kvaishnavi
commited on
Commit
•
dbeff89
1
Parent(s):
a484edc
Upload June 2024 update ONNX models
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- config.json +36 -35
- configuration_phi3.py +227 -213
- cpu_and_mobile/cpu-int4-awq-block-128/added_tokens.json +13 -0
- cpu_and_mobile/cpu-int4-awq-block-128/config.json +36 -0
- cpu_and_mobile/cpu-int4-awq-block-128/configuration_phi3.py +227 -0
- cpu_and_mobile/cpu-int4-awq-block-128/genai_config.json +53 -0
- cpu_and_mobile/cpu-int4-awq-block-128/phi3-mini-4k-instruct-cpu-int4-awq-block-128.onnx +3 -0
- cpu_and_mobile/cpu-int4-awq-block-128/phi3-mini-4k-instruct-cpu-int4-awq-block-128.onnx.data +3 -0
- cpu_and_mobile/cpu-int4-awq-block-128/special_tokens_map.json +30 -0
- cpu_and_mobile/cpu-int4-awq-block-128/tokenizer.json +0 -0
- cpu_and_mobile/cpu-int4-awq-block-128/tokenizer.model +3 -0
- cpu_and_mobile/cpu-int4-awq-block-128/tokenizer_config.json +130 -0
- cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/added_tokens.json +13 -13
- cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/config.json +36 -35
- cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/configuration_phi3.py +227 -213
- cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/phi3-mini-4k-instruct-cpu-int4-rtn-block-32-acc-level-4.onnx.data +1 -1
- cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/special_tokens_map.json +30 -30
- cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/tokenizer.json +0 -0
- cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/tokenizer_config.json +130 -130
- cpu_and_mobile/cpu-int4-rtn-block-32/added_tokens.json +13 -13
- cpu_and_mobile/cpu-int4-rtn-block-32/config.json +36 -35
- cpu_and_mobile/cpu-int4-rtn-block-32/configuration_phi3.py +227 -213
- cpu_and_mobile/cpu-int4-rtn-block-32/phi3-mini-4k-instruct-cpu-int4-rtn-block-32.onnx.data +1 -1
- cpu_and_mobile/cpu-int4-rtn-block-32/special_tokens_map.json +30 -30
- cpu_and_mobile/cpu-int4-rtn-block-32/tokenizer.json +0 -0
- cpu_and_mobile/cpu-int4-rtn-block-32/tokenizer_config.json +130 -130
- cuda/cuda-fp16/added_tokens.json +13 -13
- cuda/cuda-fp16/config.json +36 -35
- cuda/cuda-fp16/configuration_phi3.py +227 -213
- cuda/cuda-fp16/genai_config.json +1 -1
- cuda/cuda-fp16/phi3-mini-4k-instruct-cuda-fp16.onnx.data +1 -1
- cuda/cuda-fp16/special_tokens_map.json +30 -30
- cuda/cuda-fp16/tokenizer.json +0 -0
- cuda/cuda-fp16/tokenizer_config.json +130 -130
- cuda/cuda-int4-awq-block-128/added_tokens.json +13 -0
- cuda/cuda-int4-awq-block-128/config.json +36 -0
- cuda/cuda-int4-awq-block-128/configuration_phi3.py +227 -0
- cuda/cuda-int4-awq-block-128/genai_config.json +59 -0
- cuda/cuda-int4-awq-block-128/phi3-mini-4k-instruct-cuda-int4-awq-block-128.onnx +3 -0
- cuda/cuda-int4-awq-block-128/phi3-mini-4k-instruct-cuda-int4-awq-block-128.onnx.data +3 -0
- cuda/cuda-int4-awq-block-128/special_tokens_map.json +30 -0
- cuda/cuda-int4-awq-block-128/tokenizer.json +0 -0
- cuda/cuda-int4-awq-block-128/tokenizer.model +3 -0
- cuda/cuda-int4-awq-block-128/tokenizer_config.json +130 -0
- cuda/cuda-int4-rtn-block-32/added_tokens.json +13 -13
- cuda/cuda-int4-rtn-block-32/config.json +36 -35
- cuda/cuda-int4-rtn-block-32/configuration_phi3.py +227 -213
- cuda/cuda-int4-rtn-block-32/genai_config.json +1 -1
- cuda/cuda-int4-rtn-block-32/phi3-mini-4k-instruct-cuda-int4-rtn-block-32.onnx.data +1 -1
- cuda/cuda-int4-rtn-block-32/special_tokens_map.json +30 -30
config.json
CHANGED
@@ -1,35 +1,36 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"architectures": [
|
4 |
-
"Phi3ForCausalLM"
|
5 |
-
],
|
6 |
-
"attention_dropout": 0.0,
|
7 |
-
"auto_map": {
|
8 |
-
"AutoConfig": "configuration_phi3.Phi3Config",
|
9 |
-
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
|
10 |
-
},
|
11 |
-
"bos_token_id": 1,
|
12 |
-
"embd_pdrop": 0.0,
|
13 |
-
"eos_token_id": 32000,
|
14 |
-
"hidden_act": "silu",
|
15 |
-
"hidden_size": 3072,
|
16 |
-
"initializer_range": 0.02,
|
17 |
-
"intermediate_size": 8192,
|
18 |
-
"max_position_embeddings": 4096,
|
19 |
-
"model_type": "phi3",
|
20 |
-
"num_attention_heads": 32,
|
21 |
-
"num_hidden_layers": 32,
|
22 |
-
"num_key_value_heads": 32,
|
23 |
-
"original_max_position_embeddings": 4096,
|
24 |
-
"pad_token_id": 32000,
|
25 |
-
"resid_pdrop": 0.0,
|
26 |
-
"rms_norm_eps": 1e-05,
|
27 |
-
"rope_scaling": null,
|
28 |
-
"rope_theta": 10000.0,
|
29 |
-
"sliding_window": 2047,
|
30 |
-
"tie_word_embeddings": false,
|
31 |
-
"torch_dtype": "bfloat16",
|
32 |
-
"transformers_version": "4.
|
33 |
-
"use_cache": true,
|
34 |
-
"
|
35 |
-
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Phi-3-mini-4k-instruct",
|
3 |
+
"architectures": [
|
4 |
+
"Phi3ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"auto_map": {
|
8 |
+
"AutoConfig": "configuration_phi3.Phi3Config",
|
9 |
+
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
|
10 |
+
},
|
11 |
+
"bos_token_id": 1,
|
12 |
+
"embd_pdrop": 0.0,
|
13 |
+
"eos_token_id": 32000,
|
14 |
+
"hidden_act": "silu",
|
15 |
+
"hidden_size": 3072,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 8192,
|
18 |
+
"max_position_embeddings": 4096,
|
19 |
+
"model_type": "phi3",
|
20 |
+
"num_attention_heads": 32,
|
21 |
+
"num_hidden_layers": 32,
|
22 |
+
"num_key_value_heads": 32,
|
23 |
+
"original_max_position_embeddings": 4096,
|
24 |
+
"pad_token_id": 32000,
|
25 |
+
"resid_pdrop": 0.0,
|
26 |
+
"rms_norm_eps": 1e-05,
|
27 |
+
"rope_scaling": null,
|
28 |
+
"rope_theta": 10000.0,
|
29 |
+
"sliding_window": 2047,
|
30 |
+
"tie_word_embeddings": false,
|
31 |
+
"torch_dtype": "bfloat16",
|
32 |
+
"transformers_version": "4.40.2",
|
33 |
+
"use_cache": true,
|
34 |
+
"attention_bias": false,
|
35 |
+
"vocab_size": 32064
|
36 |
+
}
|
configuration_phi3.py
CHANGED
@@ -1,213 +1,227 @@
|
|
1 |
-
# coding=utf-8
|
2 |
-
# Copyright 2024 Microsoft and the HuggingFace Inc. team. All rights reserved.
|
3 |
-
#
|
4 |
-
# Licensed under the Apache License, Version 2.0 (the "License");
|
5 |
-
# you may not use this file except in compliance with the License.
|
6 |
-
# You may obtain a copy of the License at
|
7 |
-
#
|
8 |
-
# http://www.apache.org/licenses/LICENSE-2.0
|
9 |
-
#
|
10 |
-
# Unless required by applicable law or agreed to in writing, software
|
11 |
-
# distributed under the License is distributed on an "AS IS" BASIS,
|
12 |
-
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
13 |
-
# See the License for the specific language governing permissions and
|
14 |
-
# limitations under the License.
|
15 |
-
|
16 |
-
""" Phi-3 model configuration"""
|
17 |
-
|
18 |
-
|
19 |
-
from transformers.configuration_utils import PretrainedConfig
|
20 |
-
from transformers.utils import logging
|
21 |
-
|
22 |
-
|
23 |
-
logger = logging.get_logger(__name__)
|
24 |
-
|
25 |
-
PHI3_PRETRAINED_CONFIG_ARCHIVE_MAP = {
|
26 |
-
"microsoft/Phi-3-mini-4k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/resolve/main/config.json",
|
27 |
-
"microsoft/Phi-3-mini-128k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/config.json",
|
28 |
-
}
|
29 |
-
|
30 |
-
|
31 |
-
class Phi3Config(PretrainedConfig):
|
32 |
-
r"""
|
33 |
-
This is the configuration class to store the configuration of a [`Phi3Model`]. It is used to instantiate a Phi-3
|
34 |
-
model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
|
35 |
-
defaults will yield a similar configuration to that of the
|
36 |
-
[microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct).
|
37 |
-
|
38 |
-
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
|
39 |
-
documentation from [`PretrainedConfig`] for more information.
|
40 |
-
|
41 |
-
Args:
|
42 |
-
vocab_size (`int`, *optional*, defaults to 32064):
|
43 |
-
Vocabulary size of the Phi-3 model. Defines the number of different tokens that can be represented by the
|
44 |
-
`inputs_ids` passed when calling [`Phi3Model`].
|
45 |
-
hidden_size (`int`, *optional*, defaults to 3072):
|
46 |
-
Dimension of the hidden representations.
|
47 |
-
intermediate_size (`int`, *optional*, defaults to 8192):
|
48 |
-
Dimension of the MLP representations.
|
49 |
-
num_hidden_layers (`int`, *optional*, defaults to 32):
|
50 |
-
Number of hidden layers in the Transformer decoder.
|
51 |
-
num_attention_heads (`int`, *optional*, defaults to 32):
|
52 |
-
Number of attention heads for each attention layer in the Transformer decoder.
|
53 |
-
num_key_value_heads (`int`, *optional*):
|
54 |
-
This is the number of key_value heads that should be used to implement Grouped Query Attention. If
|
55 |
-
`num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
|
56 |
-
`num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
|
57 |
-
converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
|
58 |
-
by meanpooling all the original heads within that group. For more details checkout [this
|
59 |
-
paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
|
60 |
-
`num_attention_heads`.
|
61 |
-
resid_pdrop (`float`, *optional*, defaults to 0.0):
|
62 |
-
Dropout probability for mlp outputs.
|
63 |
-
embd_pdrop (`int`, *optional*, defaults to 0.0):
|
64 |
-
The dropout ratio for the embeddings.
|
65 |
-
attention_dropout (`float`, *optional*, defaults to 0.0):
|
66 |
-
The dropout ratio after computing the attention scores.
|
67 |
-
hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
|
68 |
-
The non-linear activation function (function or string) in the decoder.
|
69 |
-
max_position_embeddings (`int`, *optional*, defaults to 4096):
|
70 |
-
The maximum sequence length that this model might ever be used with.
|
71 |
-
original_max_position_embeddings (`int`, *optional*, defaults to 4096):
|
72 |
-
The maximum sequence length that this model was trained with. This is used to determine the size of the
|
73 |
-
original RoPE embeddings when using long scaling.
|
74 |
-
initializer_range (`float`, *optional*, defaults to 0.02):
|
75 |
-
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
|
76 |
-
rms_norm_eps (`float`, *optional*, defaults to 1e-05):
|
77 |
-
The epsilon value used for the RMSNorm.
|
78 |
-
use_cache (`bool`, *optional*, defaults to `True`):
|
79 |
-
Whether or not the model should return the last key/values attentions (not used by all models). Only
|
80 |
-
relevant if `config.is_decoder=True`. Whether to tie weight embeddings or not.
|
81 |
-
tie_word_embeddings (`bool`, *optional*, defaults to `False`):
|
82 |
-
Whether to tie weight embeddings
|
83 |
-
rope_theta (`float`, *optional*, defaults to 10000.0):
|
84 |
-
The base period of the RoPE embeddings.
|
85 |
-
rope_scaling (`dict`, *optional*):
|
86 |
-
The scaling strategy for the RoPE embeddings. If `None`, no scaling is applied. If a dictionary, it must
|
87 |
-
contain the following keys: `type`, `short_factor` and `long_factor`. The `type` must be
|
88 |
-
the `short_factor` and `long_factor` must be lists of numbers with the same length as the hidden size
|
89 |
-
divided by the number of attention heads divided by 2.
|
90 |
-
bos_token_id (`int`, *optional*, defaults to 1):
|
91 |
-
The id of the "beginning-of-sequence" token.
|
92 |
-
eos_token_id (`int`, *optional*, defaults to 32000):
|
93 |
-
The id of the "end-of-sequence" token.
|
94 |
-
pad_token_id (`int`, *optional*, defaults to 32000):
|
95 |
-
The id of the padding token.
|
96 |
-
sliding_window (`int`, *optional*):
|
97 |
-
Sliding window attention window size. If `None`, no sliding window is applied.
|
98 |
-
|
99 |
-
Example:
|
100 |
-
|
101 |
-
```python
|
102 |
-
>>> from transformers import Phi3Model, Phi3Config
|
103 |
-
|
104 |
-
>>> # Initializing a Phi-3 style configuration
|
105 |
-
>>> configuration = Phi3Config.from_pretrained("microsoft/Phi-3-mini-4k-instruct")
|
106 |
-
|
107 |
-
>>> # Initializing a model from the configuration
|
108 |
-
>>> model = Phi3Model(configuration)
|
109 |
-
|
110 |
-
>>> # Accessing the model configuration
|
111 |
-
>>> configuration = model.config
|
112 |
-
```"""
|
113 |
-
|
114 |
-
model_type = "phi3"
|
115 |
-
keys_to_ignore_at_inference = ["past_key_values"]
|
116 |
-
|
117 |
-
def __init__(
|
118 |
-
self,
|
119 |
-
vocab_size=32064,
|
120 |
-
hidden_size=3072,
|
121 |
-
intermediate_size=8192,
|
122 |
-
num_hidden_layers=32,
|
123 |
-
num_attention_heads=32,
|
124 |
-
num_key_value_heads=None,
|
125 |
-
resid_pdrop=0.0,
|
126 |
-
embd_pdrop=0.0,
|
127 |
-
attention_dropout=0.0,
|
128 |
-
hidden_act="silu",
|
129 |
-
max_position_embeddings=4096,
|
130 |
-
original_max_position_embeddings=4096,
|
131 |
-
initializer_range=0.02,
|
132 |
-
rms_norm_eps=1e-5,
|
133 |
-
use_cache=True,
|
134 |
-
tie_word_embeddings=False,
|
135 |
-
rope_theta=10000.0,
|
136 |
-
rope_scaling=None,
|
137 |
-
bos_token_id=1,
|
138 |
-
eos_token_id=32000,
|
139 |
-
pad_token_id=32000,
|
140 |
-
sliding_window=None,
|
141 |
-
**kwargs,
|
142 |
-
):
|
143 |
-
self.vocab_size = vocab_size
|
144 |
-
self.hidden_size = hidden_size
|
145 |
-
self.intermediate_size = intermediate_size
|
146 |
-
self.num_hidden_layers = num_hidden_layers
|
147 |
-
self.num_attention_heads = num_attention_heads
|
148 |
-
|
149 |
-
if num_key_value_heads is None:
|
150 |
-
num_key_value_heads = num_attention_heads
|
151 |
-
|
152 |
-
self.num_key_value_heads = num_key_value_heads
|
153 |
-
self.resid_pdrop = resid_pdrop
|
154 |
-
self.embd_pdrop = embd_pdrop
|
155 |
-
self.attention_dropout = attention_dropout
|
156 |
-
self.hidden_act = hidden_act
|
157 |
-
self.max_position_embeddings = max_position_embeddings
|
158 |
-
self.original_max_position_embeddings = original_max_position_embeddings
|
159 |
-
self.initializer_range = initializer_range
|
160 |
-
self.rms_norm_eps = rms_norm_eps
|
161 |
-
self.use_cache = use_cache
|
162 |
-
self.rope_theta = rope_theta
|
163 |
-
self.rope_scaling = rope_scaling
|
164 |
-
self.
|
165 |
-
self.
|
166 |
-
|
167 |
-
|
168 |
-
|
169 |
-
|
170 |
-
|
171 |
-
|
172 |
-
|
173 |
-
|
174 |
-
|
175 |
-
|
176 |
-
|
177 |
-
|
178 |
-
|
179 |
-
|
180 |
-
|
181 |
-
|
182 |
-
|
183 |
-
|
184 |
-
|
185 |
-
|
186 |
-
|
187 |
-
|
188 |
-
|
189 |
-
|
190 |
-
|
191 |
-
|
192 |
-
|
193 |
-
|
194 |
-
|
195 |
-
|
196 |
-
|
197 |
-
|
198 |
-
|
199 |
-
|
200 |
-
|
201 |
-
|
202 |
-
|
203 |
-
|
204 |
-
|
205 |
-
|
206 |
-
|
207 |
-
|
208 |
-
|
209 |
-
|
210 |
-
|
211 |
-
|
212 |
-
|
213 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# coding=utf-8
|
2 |
+
# Copyright 2024 Microsoft and the HuggingFace Inc. team. All rights reserved.
|
3 |
+
#
|
4 |
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
5 |
+
# you may not use this file except in compliance with the License.
|
6 |
+
# You may obtain a copy of the License at
|
7 |
+
#
|
8 |
+
# http://www.apache.org/licenses/LICENSE-2.0
|
9 |
+
#
|
10 |
+
# Unless required by applicable law or agreed to in writing, software
|
11 |
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
12 |
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
13 |
+
# See the License for the specific language governing permissions and
|
14 |
+
# limitations under the License.
|
15 |
+
|
16 |
+
""" Phi-3 model configuration"""
|
17 |
+
|
18 |
+
|
19 |
+
from transformers.configuration_utils import PretrainedConfig
|
20 |
+
from transformers.utils import logging
|
21 |
+
|
22 |
+
|
23 |
+
logger = logging.get_logger(__name__)
|
24 |
+
|
25 |
+
PHI3_PRETRAINED_CONFIG_ARCHIVE_MAP = {
|
26 |
+
"microsoft/Phi-3-mini-4k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/resolve/main/config.json",
|
27 |
+
"microsoft/Phi-3-mini-128k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/config.json",
|
28 |
+
}
|
29 |
+
|
30 |
+
|
31 |
+
class Phi3Config(PretrainedConfig):
|
32 |
+
r"""
|
33 |
+
This is the configuration class to store the configuration of a [`Phi3Model`]. It is used to instantiate a Phi-3
|
34 |
+
model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
|
35 |
+
defaults will yield a similar configuration to that of the
|
36 |
+
[microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct).
|
37 |
+
|
38 |
+
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
|
39 |
+
documentation from [`PretrainedConfig`] for more information.
|
40 |
+
|
41 |
+
Args:
|
42 |
+
vocab_size (`int`, *optional*, defaults to 32064):
|
43 |
+
Vocabulary size of the Phi-3 model. Defines the number of different tokens that can be represented by the
|
44 |
+
`inputs_ids` passed when calling [`Phi3Model`].
|
45 |
+
hidden_size (`int`, *optional*, defaults to 3072):
|
46 |
+
Dimension of the hidden representations.
|
47 |
+
intermediate_size (`int`, *optional*, defaults to 8192):
|
48 |
+
Dimension of the MLP representations.
|
49 |
+
num_hidden_layers (`int`, *optional*, defaults to 32):
|
50 |
+
Number of hidden layers in the Transformer decoder.
|
51 |
+
num_attention_heads (`int`, *optional*, defaults to 32):
|
52 |
+
Number of attention heads for each attention layer in the Transformer decoder.
|
53 |
+
num_key_value_heads (`int`, *optional*):
|
54 |
+
This is the number of key_value heads that should be used to implement Grouped Query Attention. If
|
55 |
+
`num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
|
56 |
+
`num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
|
57 |
+
converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
|
58 |
+
by meanpooling all the original heads within that group. For more details checkout [this
|
59 |
+
paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
|
60 |
+
`num_attention_heads`.
|
61 |
+
resid_pdrop (`float`, *optional*, defaults to 0.0):
|
62 |
+
Dropout probability for mlp outputs.
|
63 |
+
embd_pdrop (`int`, *optional*, defaults to 0.0):
|
64 |
+
The dropout ratio for the embeddings.
|
65 |
+
attention_dropout (`float`, *optional*, defaults to 0.0):
|
66 |
+
The dropout ratio after computing the attention scores.
|
67 |
+
hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
|
68 |
+
The non-linear activation function (function or string) in the decoder.
|
69 |
+
max_position_embeddings (`int`, *optional*, defaults to 4096):
|
70 |
+
The maximum sequence length that this model might ever be used with.
|
71 |
+
original_max_position_embeddings (`int`, *optional*, defaults to 4096):
|
72 |
+
The maximum sequence length that this model was trained with. This is used to determine the size of the
|
73 |
+
original RoPE embeddings when using long scaling.
|
74 |
+
initializer_range (`float`, *optional*, defaults to 0.02):
|
75 |
+
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
|
76 |
+
rms_norm_eps (`float`, *optional*, defaults to 1e-05):
|
77 |
+
The epsilon value used for the RMSNorm.
|
78 |
+
use_cache (`bool`, *optional*, defaults to `True`):
|
79 |
+
Whether or not the model should return the last key/values attentions (not used by all models). Only
|
80 |
+
relevant if `config.is_decoder=True`. Whether to tie weight embeddings or not.
|
81 |
+
tie_word_embeddings (`bool`, *optional*, defaults to `False`):
|
82 |
+
Whether to tie weight embeddings
|
83 |
+
rope_theta (`float`, *optional*, defaults to 10000.0):
|
84 |
+
The base period of the RoPE embeddings.
|
85 |
+
rope_scaling (`dict`, *optional*):
|
86 |
+
The scaling strategy for the RoPE embeddings. If `None`, no scaling is applied. If a dictionary, it must
|
87 |
+
contain the following keys: `type`, `short_factor` and `long_factor`. The `type` must be `longrope` and
|
88 |
+
the `short_factor` and `long_factor` must be lists of numbers with the same length as the hidden size
|
89 |
+
divided by the number of attention heads divided by 2.
|
90 |
+
bos_token_id (`int`, *optional*, defaults to 1):
|
91 |
+
The id of the "beginning-of-sequence" token.
|
92 |
+
eos_token_id (`int`, *optional*, defaults to 32000):
|
93 |
+
The id of the "end-of-sequence" token.
|
94 |
+
pad_token_id (`int`, *optional*, defaults to 32000):
|
95 |
+
The id of the padding token.
|
96 |
+
sliding_window (`int`, *optional*):
|
97 |
+
Sliding window attention window size. If `None`, no sliding window is applied.
|
98 |
+
|
99 |
+
Example:
|
100 |
+
|
101 |
+
```python
|
102 |
+
>>> from transformers import Phi3Model, Phi3Config
|
103 |
+
|
104 |
+
>>> # Initializing a Phi-3 style configuration
|
105 |
+
>>> configuration = Phi3Config.from_pretrained("microsoft/Phi-3-mini-4k-instruct")
|
106 |
+
|
107 |
+
>>> # Initializing a model from the configuration
|
108 |
+
>>> model = Phi3Model(configuration)
|
109 |
+
|
110 |
+
>>> # Accessing the model configuration
|
111 |
+
>>> configuration = model.config
|
112 |
+
```"""
|
113 |
+
|
114 |
+
model_type = "phi3"
|
115 |
+
keys_to_ignore_at_inference = ["past_key_values"]
|
116 |
+
|
117 |
+
def __init__(
|
118 |
+
self,
|
119 |
+
vocab_size=32064,
|
120 |
+
hidden_size=3072,
|
121 |
+
intermediate_size=8192,
|
122 |
+
num_hidden_layers=32,
|
123 |
+
num_attention_heads=32,
|
124 |
+
num_key_value_heads=None,
|
125 |
+
resid_pdrop=0.0,
|
126 |
+
embd_pdrop=0.0,
|
127 |
+
attention_dropout=0.0,
|
128 |
+
hidden_act="silu",
|
129 |
+
max_position_embeddings=4096,
|
130 |
+
original_max_position_embeddings=4096,
|
131 |
+
initializer_range=0.02,
|
132 |
+
rms_norm_eps=1e-5,
|
133 |
+
use_cache=True,
|
134 |
+
tie_word_embeddings=False,
|
135 |
+
rope_theta=10000.0,
|
136 |
+
rope_scaling=None,
|
137 |
+
bos_token_id=1,
|
138 |
+
eos_token_id=32000,
|
139 |
+
pad_token_id=32000,
|
140 |
+
sliding_window=None,
|
141 |
+
**kwargs,
|
142 |
+
):
|
143 |
+
self.vocab_size = vocab_size
|
144 |
+
self.hidden_size = hidden_size
|
145 |
+
self.intermediate_size = intermediate_size
|
146 |
+
self.num_hidden_layers = num_hidden_layers
|
147 |
+
self.num_attention_heads = num_attention_heads
|
148 |
+
|
149 |
+
if num_key_value_heads is None:
|
150 |
+
num_key_value_heads = num_attention_heads
|
151 |
+
|
152 |
+
self.num_key_value_heads = num_key_value_heads
|
153 |
+
self.resid_pdrop = resid_pdrop
|
154 |
+
self.embd_pdrop = embd_pdrop
|
155 |
+
self.attention_dropout = attention_dropout
|
156 |
+
self.hidden_act = hidden_act
|
157 |
+
self.max_position_embeddings = max_position_embeddings
|
158 |
+
self.original_max_position_embeddings = original_max_position_embeddings
|
159 |
+
self.initializer_range = initializer_range
|
160 |
+
self.rms_norm_eps = rms_norm_eps
|
161 |
+
self.use_cache = use_cache
|
162 |
+
self.rope_theta = rope_theta
|
163 |
+
self.rope_scaling = rope_scaling
|
164 |
+
self._rope_scaling_adjustment()
|
165 |
+
self._rope_scaling_validation()
|
166 |
+
self.sliding_window = sliding_window
|
167 |
+
|
168 |
+
super().__init__(
|
169 |
+
bos_token_id=bos_token_id,
|
170 |
+
eos_token_id=eos_token_id,
|
171 |
+
pad_token_id=pad_token_id,
|
172 |
+
tie_word_embeddings=tie_word_embeddings,
|
173 |
+
**kwargs,
|
174 |
+
)
|
175 |
+
|
176 |
+
def _rope_scaling_adjustment(self):
|
177 |
+
"""
|
178 |
+
Adjust the `type` of the `rope_scaling` configuration for backward compatibility.
|
179 |
+
"""
|
180 |
+
if self.rope_scaling is None:
|
181 |
+
return
|
182 |
+
|
183 |
+
rope_scaling_type = self.rope_scaling.get("type", None)
|
184 |
+
|
185 |
+
# For backward compatibility if previous version used "su" or "yarn"
|
186 |
+
if rope_scaling_type is not None and rope_scaling_type in ["su", "yarn"]:
|
187 |
+
self.rope_scaling["type"] = "longrope"
|
188 |
+
|
189 |
+
def _rope_scaling_validation(self):
|
190 |
+
"""
|
191 |
+
Validate the `rope_scaling` configuration.
|
192 |
+
"""
|
193 |
+
if self.rope_scaling is None:
|
194 |
+
return
|
195 |
+
|
196 |
+
if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 3:
|
197 |
+
raise ValueError(
|
198 |
+
"`rope_scaling` must be a dictionary with three fields, `type`, `short_factor` and `long_factor`, "
|
199 |
+
f"got {self.rope_scaling}"
|
200 |
+
)
|
201 |
+
rope_scaling_type = self.rope_scaling.get("type", None)
|
202 |
+
rope_scaling_short_factor = self.rope_scaling.get("short_factor", None)
|
203 |
+
rope_scaling_long_factor = self.rope_scaling.get("long_factor", None)
|
204 |
+
if rope_scaling_type is None or rope_scaling_type not in ["longrope"]:
|
205 |
+
raise ValueError(f"`rope_scaling`'s type field must be one of ['longrope'], got {rope_scaling_type}")
|
206 |
+
if not (
|
207 |
+
isinstance(rope_scaling_short_factor, list)
|
208 |
+
and all(isinstance(x, (int, float)) for x in rope_scaling_short_factor)
|
209 |
+
):
|
210 |
+
raise ValueError(
|
211 |
+
f"`rope_scaling`'s short_factor field must be a list of numbers, got {rope_scaling_short_factor}"
|
212 |
+
)
|
213 |
+
if not len(rope_scaling_short_factor) == self.hidden_size // self.num_attention_heads // 2:
|
214 |
+
raise ValueError(
|
215 |
+
f"`rope_scaling`'s short_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_short_factor)}"
|
216 |
+
)
|
217 |
+
if not (
|
218 |
+
isinstance(rope_scaling_long_factor, list)
|
219 |
+
and all(isinstance(x, (int, float)) for x in rope_scaling_long_factor)
|
220 |
+
):
|
221 |
+
raise ValueError(
|
222 |
+
f"`rope_scaling`'s long_factor field must be a list of numbers, got {rope_scaling_long_factor}"
|
223 |
+
)
|
224 |
+
if not len(rope_scaling_long_factor) == self.hidden_size // self.num_attention_heads // 2:
|
225 |
+
raise ValueError(
|
226 |
+
f"`rope_scaling`'s long_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_long_factor)}"
|
227 |
+
)
|
cpu_and_mobile/cpu-int4-awq-block-128/added_tokens.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 32000,
|
3 |
+
"<|assistant|>": 32001,
|
4 |
+
"<|placeholder1|>": 32002,
|
5 |
+
"<|placeholder2|>": 32003,
|
6 |
+
"<|placeholder3|>": 32004,
|
7 |
+
"<|placeholder4|>": 32005,
|
8 |
+
"<|system|>": 32006,
|
9 |
+
"<|end|>": 32007,
|
10 |
+
"<|placeholder5|>": 32008,
|
11 |
+
"<|placeholder6|>": 32009,
|
12 |
+
"<|user|>": 32010
|
13 |
+
}
|
cpu_and_mobile/cpu-int4-awq-block-128/config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Phi-3-mini-4k-instruct",
|
3 |
+
"architectures": [
|
4 |
+
"Phi3ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"auto_map": {
|
8 |
+
"AutoConfig": "configuration_phi3.Phi3Config",
|
9 |
+
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
|
10 |
+
},
|
11 |
+
"bos_token_id": 1,
|
12 |
+
"embd_pdrop": 0.0,
|
13 |
+
"eos_token_id": 32000,
|
14 |
+
"hidden_act": "silu",
|
15 |
+
"hidden_size": 3072,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 8192,
|
18 |
+
"max_position_embeddings": 4096,
|
19 |
+
"model_type": "phi3",
|
20 |
+
"num_attention_heads": 32,
|
21 |
+
"num_hidden_layers": 32,
|
22 |
+
"num_key_value_heads": 32,
|
23 |
+
"original_max_position_embeddings": 4096,
|
24 |
+
"pad_token_id": 32000,
|
25 |
+
"resid_pdrop": 0.0,
|
26 |
+
"rms_norm_eps": 1e-05,
|
27 |
+
"rope_scaling": null,
|
28 |
+
"rope_theta": 10000.0,
|
29 |
+
"sliding_window": 2047,
|
30 |
+
"tie_word_embeddings": false,
|
31 |
+
"torch_dtype": "bfloat16",
|
32 |
+
"transformers_version": "4.40.2",
|
33 |
+
"use_cache": true,
|
34 |
+
"attention_bias": false,
|
35 |
+
"vocab_size": 32064
|
36 |
+
}
|
cpu_and_mobile/cpu-int4-awq-block-128/configuration_phi3.py
ADDED
@@ -0,0 +1,227 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# coding=utf-8
|
2 |
+
# Copyright 2024 Microsoft and the HuggingFace Inc. team. All rights reserved.
|
3 |
+
#
|
4 |
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
5 |
+
# you may not use this file except in compliance with the License.
|
6 |
+
# You may obtain a copy of the License at
|
7 |
+
#
|
8 |
+
# http://www.apache.org/licenses/LICENSE-2.0
|
9 |
+
#
|
10 |
+
# Unless required by applicable law or agreed to in writing, software
|
11 |
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
12 |
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
13 |
+
# See the License for the specific language governing permissions and
|
14 |
+
# limitations under the License.
|
15 |
+
|
16 |
+
""" Phi-3 model configuration"""
|
17 |
+
|
18 |
+
|
19 |
+
from transformers.configuration_utils import PretrainedConfig
|
20 |
+
from transformers.utils import logging
|
21 |
+
|
22 |
+
|
23 |
+
logger = logging.get_logger(__name__)
|
24 |
+
|
25 |
+
PHI3_PRETRAINED_CONFIG_ARCHIVE_MAP = {
|
26 |
+
"microsoft/Phi-3-mini-4k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/resolve/main/config.json",
|
27 |
+
"microsoft/Phi-3-mini-128k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/config.json",
|
28 |
+
}
|
29 |
+
|
30 |
+
|
31 |
+
class Phi3Config(PretrainedConfig):
|
32 |
+
r"""
|
33 |
+
This is the configuration class to store the configuration of a [`Phi3Model`]. It is used to instantiate a Phi-3
|
34 |
+
model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
|
35 |
+
defaults will yield a similar configuration to that of the
|
36 |
+
[microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct).
|
37 |
+
|
38 |
+
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
|
39 |
+
documentation from [`PretrainedConfig`] for more information.
|
40 |
+
|
41 |
+
Args:
|
42 |
+
vocab_size (`int`, *optional*, defaults to 32064):
|
43 |
+
Vocabulary size of the Phi-3 model. Defines the number of different tokens that can be represented by the
|
44 |
+
`inputs_ids` passed when calling [`Phi3Model`].
|
45 |
+
hidden_size (`int`, *optional*, defaults to 3072):
|
46 |
+
Dimension of the hidden representations.
|
47 |
+
intermediate_size (`int`, *optional*, defaults to 8192):
|
48 |
+
Dimension of the MLP representations.
|
49 |
+
num_hidden_layers (`int`, *optional*, defaults to 32):
|
50 |
+
Number of hidden layers in the Transformer decoder.
|
51 |
+
num_attention_heads (`int`, *optional*, defaults to 32):
|
52 |
+
Number of attention heads for each attention layer in the Transformer decoder.
|
53 |
+
num_key_value_heads (`int`, *optional*):
|
54 |
+
This is the number of key_value heads that should be used to implement Grouped Query Attention. If
|
55 |
+
`num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
|
56 |
+
`num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
|
57 |
+
converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
|
58 |
+
by meanpooling all the original heads within that group. For more details checkout [this
|
59 |
+
paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
|
60 |
+
`num_attention_heads`.
|
61 |
+
resid_pdrop (`float`, *optional*, defaults to 0.0):
|
62 |
+
Dropout probability for mlp outputs.
|
63 |
+
embd_pdrop (`int`, *optional*, defaults to 0.0):
|
64 |
+
The dropout ratio for the embeddings.
|
65 |
+
attention_dropout (`float`, *optional*, defaults to 0.0):
|
66 |
+
The dropout ratio after computing the attention scores.
|
67 |
+
hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
|
68 |
+
The non-linear activation function (function or string) in the decoder.
|
69 |
+
max_position_embeddings (`int`, *optional*, defaults to 4096):
|
70 |
+
The maximum sequence length that this model might ever be used with.
|
71 |
+
original_max_position_embeddings (`int`, *optional*, defaults to 4096):
|
72 |
+
The maximum sequence length that this model was trained with. This is used to determine the size of the
|
73 |
+
original RoPE embeddings when using long scaling.
|
74 |
+
initializer_range (`float`, *optional*, defaults to 0.02):
|
75 |
+
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
|
76 |
+
rms_norm_eps (`float`, *optional*, defaults to 1e-05):
|
77 |
+
The epsilon value used for the RMSNorm.
|
78 |
+
use_cache (`bool`, *optional*, defaults to `True`):
|
79 |
+
Whether or not the model should return the last key/values attentions (not used by all models). Only
|
80 |
+
relevant if `config.is_decoder=True`. Whether to tie weight embeddings or not.
|
81 |
+
tie_word_embeddings (`bool`, *optional*, defaults to `False`):
|
82 |
+
Whether to tie weight embeddings
|
83 |
+
rope_theta (`float`, *optional*, defaults to 10000.0):
|
84 |
+
The base period of the RoPE embeddings.
|
85 |
+
rope_scaling (`dict`, *optional*):
|
86 |
+
The scaling strategy for the RoPE embeddings. If `None`, no scaling is applied. If a dictionary, it must
|
87 |
+
contain the following keys: `type`, `short_factor` and `long_factor`. The `type` must be `longrope` and
|
88 |
+
the `short_factor` and `long_factor` must be lists of numbers with the same length as the hidden size
|
89 |
+
divided by the number of attention heads divided by 2.
|
90 |
+
bos_token_id (`int`, *optional*, defaults to 1):
|
91 |
+
The id of the "beginning-of-sequence" token.
|
92 |
+
eos_token_id (`int`, *optional*, defaults to 32000):
|
93 |
+
The id of the "end-of-sequence" token.
|
94 |
+
pad_token_id (`int`, *optional*, defaults to 32000):
|
95 |
+
The id of the padding token.
|
96 |
+
sliding_window (`int`, *optional*):
|
97 |
+
Sliding window attention window size. If `None`, no sliding window is applied.
|
98 |
+
|
99 |
+
Example:
|
100 |
+
|
101 |
+
```python
|
102 |
+
>>> from transformers import Phi3Model, Phi3Config
|
103 |
+
|
104 |
+
>>> # Initializing a Phi-3 style configuration
|
105 |
+
>>> configuration = Phi3Config.from_pretrained("microsoft/Phi-3-mini-4k-instruct")
|
106 |
+
|
107 |
+
>>> # Initializing a model from the configuration
|
108 |
+
>>> model = Phi3Model(configuration)
|
109 |
+
|
110 |
+
>>> # Accessing the model configuration
|
111 |
+
>>> configuration = model.config
|
112 |
+
```"""
|
113 |
+
|
114 |
+
model_type = "phi3"
|
115 |
+
keys_to_ignore_at_inference = ["past_key_values"]
|
116 |
+
|
117 |
+
def __init__(
|
118 |
+
self,
|
119 |
+
vocab_size=32064,
|
120 |
+
hidden_size=3072,
|
121 |
+
intermediate_size=8192,
|
122 |
+
num_hidden_layers=32,
|
123 |
+
num_attention_heads=32,
|
124 |
+
num_key_value_heads=None,
|
125 |
+
resid_pdrop=0.0,
|
126 |
+
embd_pdrop=0.0,
|
127 |
+
attention_dropout=0.0,
|
128 |
+
hidden_act="silu",
|
129 |
+
max_position_embeddings=4096,
|
130 |
+
original_max_position_embeddings=4096,
|
131 |
+
initializer_range=0.02,
|
132 |
+
rms_norm_eps=1e-5,
|
133 |
+
use_cache=True,
|
134 |
+
tie_word_embeddings=False,
|
135 |
+
rope_theta=10000.0,
|
136 |
+
rope_scaling=None,
|
137 |
+
bos_token_id=1,
|
138 |
+
eos_token_id=32000,
|
139 |
+
pad_token_id=32000,
|
140 |
+
sliding_window=None,
|
141 |
+
**kwargs,
|
142 |
+
):
|
143 |
+
self.vocab_size = vocab_size
|
144 |
+
self.hidden_size = hidden_size
|
145 |
+
self.intermediate_size = intermediate_size
|
146 |
+
self.num_hidden_layers = num_hidden_layers
|
147 |
+
self.num_attention_heads = num_attention_heads
|
148 |
+
|
149 |
+
if num_key_value_heads is None:
|
150 |
+
num_key_value_heads = num_attention_heads
|
151 |
+
|
152 |
+
self.num_key_value_heads = num_key_value_heads
|
153 |
+
self.resid_pdrop = resid_pdrop
|
154 |
+
self.embd_pdrop = embd_pdrop
|
155 |
+
self.attention_dropout = attention_dropout
|
156 |
+
self.hidden_act = hidden_act
|
157 |
+
self.max_position_embeddings = max_position_embeddings
|
158 |
+
self.original_max_position_embeddings = original_max_position_embeddings
|
159 |
+
self.initializer_range = initializer_range
|
160 |
+
self.rms_norm_eps = rms_norm_eps
|
161 |
+
self.use_cache = use_cache
|
162 |
+
self.rope_theta = rope_theta
|
163 |
+
self.rope_scaling = rope_scaling
|
164 |
+
self._rope_scaling_adjustment()
|
165 |
+
self._rope_scaling_validation()
|
166 |
+
self.sliding_window = sliding_window
|
167 |
+
|
168 |
+
super().__init__(
|
169 |
+
bos_token_id=bos_token_id,
|
170 |
+
eos_token_id=eos_token_id,
|
171 |
+
pad_token_id=pad_token_id,
|
172 |
+
tie_word_embeddings=tie_word_embeddings,
|
173 |
+
**kwargs,
|
174 |
+
)
|
175 |
+
|
176 |
+
def _rope_scaling_adjustment(self):
|
177 |
+
"""
|
178 |
+
Adjust the `type` of the `rope_scaling` configuration for backward compatibility.
|
179 |
+
"""
|
180 |
+
if self.rope_scaling is None:
|
181 |
+
return
|
182 |
+
|
183 |
+
rope_scaling_type = self.rope_scaling.get("type", None)
|
184 |
+
|
185 |
+
# For backward compatibility if previous version used "su" or "yarn"
|
186 |
+
if rope_scaling_type is not None and rope_scaling_type in ["su", "yarn"]:
|
187 |
+
self.rope_scaling["type"] = "longrope"
|
188 |
+
|
189 |
+
def _rope_scaling_validation(self):
|
190 |
+
"""
|
191 |
+
Validate the `rope_scaling` configuration.
|
192 |
+
"""
|
193 |
+
if self.rope_scaling is None:
|
194 |
+
return
|
195 |
+
|
196 |
+
if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 3:
|
197 |
+
raise ValueError(
|
198 |
+
"`rope_scaling` must be a dictionary with three fields, `type`, `short_factor` and `long_factor`, "
|
199 |
+
f"got {self.rope_scaling}"
|
200 |
+
)
|
201 |
+
rope_scaling_type = self.rope_scaling.get("type", None)
|
202 |
+
rope_scaling_short_factor = self.rope_scaling.get("short_factor", None)
|
203 |
+
rope_scaling_long_factor = self.rope_scaling.get("long_factor", None)
|
204 |
+
if rope_scaling_type is None or rope_scaling_type not in ["longrope"]:
|
205 |
+
raise ValueError(f"`rope_scaling`'s type field must be one of ['longrope'], got {rope_scaling_type}")
|
206 |
+
if not (
|
207 |
+
isinstance(rope_scaling_short_factor, list)
|
208 |
+
and all(isinstance(x, (int, float)) for x in rope_scaling_short_factor)
|
209 |
+
):
|
210 |
+
raise ValueError(
|
211 |
+
f"`rope_scaling`'s short_factor field must be a list of numbers, got {rope_scaling_short_factor}"
|
212 |
+
)
|
213 |
+
if not len(rope_scaling_short_factor) == self.hidden_size // self.num_attention_heads // 2:
|
214 |
+
raise ValueError(
|
215 |
+
f"`rope_scaling`'s short_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_short_factor)}"
|
216 |
+
)
|
217 |
+
if not (
|
218 |
+
isinstance(rope_scaling_long_factor, list)
|
219 |
+
and all(isinstance(x, (int, float)) for x in rope_scaling_long_factor)
|
220 |
+
):
|
221 |
+
raise ValueError(
|
222 |
+
f"`rope_scaling`'s long_factor field must be a list of numbers, got {rope_scaling_long_factor}"
|
223 |
+
)
|
224 |
+
if not len(rope_scaling_long_factor) == self.hidden_size // self.num_attention_heads // 2:
|
225 |
+
raise ValueError(
|
226 |
+
f"`rope_scaling`'s long_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_long_factor)}"
|
227 |
+
)
|
cpu_and_mobile/cpu-int4-awq-block-128/genai_config.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model": {
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"context_length": 4096,
|
5 |
+
"decoder": {
|
6 |
+
"session_options": {
|
7 |
+
"log_id": "onnxruntime-genai",
|
8 |
+
"provider_options": []
|
9 |
+
},
|
10 |
+
"filename": "phi3-mini-4k-instruct-cpu-int4-awq-block-128.onnx",
|
11 |
+
"head_size": 96,
|
12 |
+
"hidden_size": 3072,
|
13 |
+
"inputs": {
|
14 |
+
"input_ids": "input_ids",
|
15 |
+
"attention_mask": "attention_mask",
|
16 |
+
"past_key_names": "past_key_values.%d.key",
|
17 |
+
"past_value_names": "past_key_values.%d.value"
|
18 |
+
},
|
19 |
+
"outputs": {
|
20 |
+
"logits": "logits",
|
21 |
+
"present_key_names": "present.%d.key",
|
22 |
+
"present_value_names": "present.%d.value"
|
23 |
+
},
|
24 |
+
"num_attention_heads": 32,
|
25 |
+
"num_hidden_layers": 32,
|
26 |
+
"num_key_value_heads": 32
|
27 |
+
},
|
28 |
+
"eos_token_id": [
|
29 |
+
32000,
|
30 |
+
32001,
|
31 |
+
32007
|
32 |
+
],
|
33 |
+
"pad_token_id": 32000,
|
34 |
+
"type": "phi3",
|
35 |
+
"vocab_size": 32064
|
36 |
+
},
|
37 |
+
"search": {
|
38 |
+
"diversity_penalty": 0.0,
|
39 |
+
"do_sample": false,
|
40 |
+
"early_stopping": true,
|
41 |
+
"length_penalty": 1.0,
|
42 |
+
"max_length": 4096,
|
43 |
+
"min_length": 0,
|
44 |
+
"no_repeat_ngram_size": 0,
|
45 |
+
"num_beams": 1,
|
46 |
+
"num_return_sequences": 1,
|
47 |
+
"past_present_share_buffer": true,
|
48 |
+
"repetition_penalty": 1.0,
|
49 |
+
"temperature": 1.0,
|
50 |
+
"top_k": 1,
|
51 |
+
"top_p": 1.0
|
52 |
+
}
|
53 |
+
}
|
cpu_and_mobile/cpu-int4-awq-block-128/phi3-mini-4k-instruct-cpu-int4-awq-block-128.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ef7369cf4807ea6c0e4b8f20c560213429618df45e6a23696d1e6ba5886271f
|
3 |
+
size 260780
|
cpu_and_mobile/cpu-int4-awq-block-128/phi3-mini-4k-instruct-cpu-int4-awq-block-128.onnx.data
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad837e05501fd5c3d8d84e05defead37dad3d1b8e3749a7fc11734e1f415506f
|
3 |
+
size 2729717760
|
cpu_and_mobile/cpu-int4-awq-block-128/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
cpu_and_mobile/cpu-int4-awq-block-128/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
cpu_and_mobile/cpu-int4-awq-block-128/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
cpu_and_mobile/cpu-int4-awq-block-128/tokenizer_config.json
ADDED
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": true,
|
26 |
+
"single_word": false,
|
27 |
+
"special": false
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "<|endoftext|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"32001": {
|
38 |
+
"content": "<|assistant|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": true,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"32002": {
|
46 |
+
"content": "<|placeholder1|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": true,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"32003": {
|
54 |
+
"content": "<|placeholder2|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": true,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"32004": {
|
62 |
+
"content": "<|placeholder3|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": true,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"32005": {
|
70 |
+
"content": "<|placeholder4|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": true,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"32006": {
|
78 |
+
"content": "<|system|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": true,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"32007": {
|
86 |
+
"content": "<|end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": true,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"32008": {
|
94 |
+
"content": "<|placeholder5|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": true,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"32009": {
|
102 |
+
"content": "<|placeholder6|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": true,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"32010": {
|
110 |
+
"content": "<|user|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": true,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
}
|
117 |
+
},
|
118 |
+
"bos_token": "<s>",
|
119 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
|
120 |
+
"clean_up_tokenization_spaces": false,
|
121 |
+
"eos_token": "<|endoftext|>",
|
122 |
+
"legacy": false,
|
123 |
+
"model_max_length": 4096,
|
124 |
+
"pad_token": "<|endoftext|>",
|
125 |
+
"padding_side": "left",
|
126 |
+
"sp_model_kwargs": {},
|
127 |
+
"tokenizer_class": "LlamaTokenizer",
|
128 |
+
"unk_token": "<unk>",
|
129 |
+
"use_default_system_prompt": false
|
130 |
+
}
|
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/added_tokens.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
-
{
|
2 |
-
"<|endoftext|>": 32000,
|
3 |
-
"<|assistant|>": 32001,
|
4 |
-
"<|placeholder1|>": 32002,
|
5 |
-
"<|placeholder2|>": 32003,
|
6 |
-
"<|placeholder3|>": 32004,
|
7 |
-
"<|placeholder4|>": 32005,
|
8 |
-
"<|system|>": 32006,
|
9 |
-
"<|end|>": 32007,
|
10 |
-
"<|placeholder5|>": 32008,
|
11 |
-
"<|placeholder6|>": 32009,
|
12 |
-
"<|user|>": 32010
|
13 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 32000,
|
3 |
+
"<|assistant|>": 32001,
|
4 |
+
"<|placeholder1|>": 32002,
|
5 |
+
"<|placeholder2|>": 32003,
|
6 |
+
"<|placeholder3|>": 32004,
|
7 |
+
"<|placeholder4|>": 32005,
|
8 |
+
"<|system|>": 32006,
|
9 |
+
"<|end|>": 32007,
|
10 |
+
"<|placeholder5|>": 32008,
|
11 |
+
"<|placeholder6|>": 32009,
|
12 |
+
"<|user|>": 32010
|
13 |
+
}
|
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/config.json
CHANGED
@@ -1,35 +1,36 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"architectures": [
|
4 |
-
"Phi3ForCausalLM"
|
5 |
-
],
|
6 |
-
"attention_dropout": 0.0,
|
7 |
-
"auto_map": {
|
8 |
-
"AutoConfig": "configuration_phi3.Phi3Config",
|
9 |
-
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
|
10 |
-
},
|
11 |
-
"bos_token_id": 1,
|
12 |
-
"embd_pdrop": 0.0,
|
13 |
-
"eos_token_id": 32000,
|
14 |
-
"hidden_act": "silu",
|
15 |
-
"hidden_size": 3072,
|
16 |
-
"initializer_range": 0.02,
|
17 |
-
"intermediate_size": 8192,
|
18 |
-
"max_position_embeddings": 4096,
|
19 |
-
"model_type": "phi3",
|
20 |
-
"num_attention_heads": 32,
|
21 |
-
"num_hidden_layers": 32,
|
22 |
-
"num_key_value_heads": 32,
|
23 |
-
"original_max_position_embeddings": 4096,
|
24 |
-
"pad_token_id": 32000,
|
25 |
-
"resid_pdrop": 0.0,
|
26 |
-
"rms_norm_eps": 1e-05,
|
27 |
-
"rope_scaling": null,
|
28 |
-
"rope_theta": 10000.0,
|
29 |
-
"sliding_window": 2047,
|
30 |
-
"tie_word_embeddings": false,
|
31 |
-
"torch_dtype": "bfloat16",
|
32 |
-
"transformers_version": "4.
|
33 |
-
"use_cache": true,
|
34 |
-
"
|
35 |
-
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Phi-3-mini-4k-instruct",
|
3 |
+
"architectures": [
|
4 |
+
"Phi3ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"auto_map": {
|
8 |
+
"AutoConfig": "configuration_phi3.Phi3Config",
|
9 |
+
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
|
10 |
+
},
|
11 |
+
"bos_token_id": 1,
|
12 |
+
"embd_pdrop": 0.0,
|
13 |
+
"eos_token_id": 32000,
|
14 |
+
"hidden_act": "silu",
|
15 |
+
"hidden_size": 3072,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 8192,
|
18 |
+
"max_position_embeddings": 4096,
|
19 |
+
"model_type": "phi3",
|
20 |
+
"num_attention_heads": 32,
|
21 |
+
"num_hidden_layers": 32,
|
22 |
+
"num_key_value_heads": 32,
|
23 |
+
"original_max_position_embeddings": 4096,
|
24 |
+
"pad_token_id": 32000,
|
25 |
+
"resid_pdrop": 0.0,
|
26 |
+
"rms_norm_eps": 1e-05,
|
27 |
+
"rope_scaling": null,
|
28 |
+
"rope_theta": 10000.0,
|
29 |
+
"sliding_window": 2047,
|
30 |
+
"tie_word_embeddings": false,
|
31 |
+
"torch_dtype": "bfloat16",
|
32 |
+
"transformers_version": "4.40.2",
|
33 |
+
"use_cache": true,
|
34 |
+
"attention_bias": false,
|
35 |
+
"vocab_size": 32064
|
36 |
+
}
|
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/configuration_phi3.py
CHANGED
@@ -1,213 +1,227 @@
|
|
1 |
-
# coding=utf-8
|
2 |
-
# Copyright 2024 Microsoft and the HuggingFace Inc. team. All rights reserved.
|
3 |
-
#
|
4 |
-
# Licensed under the Apache License, Version 2.0 (the "License");
|
5 |
-
# you may not use this file except in compliance with the License.
|
6 |
-
# You may obtain a copy of the License at
|
7 |
-
#
|
8 |
-
# http://www.apache.org/licenses/LICENSE-2.0
|
9 |
-
#
|
10 |
-
# Unless required by applicable law or agreed to in writing, software
|
11 |
-
# distributed under the License is distributed on an "AS IS" BASIS,
|
12 |
-
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
13 |
-
# See the License for the specific language governing permissions and
|
14 |
-
# limitations under the License.
|
15 |
-
|
16 |
-
""" Phi-3 model configuration"""
|
17 |
-
|
18 |
-
|
19 |
-
from transformers.configuration_utils import PretrainedConfig
|
20 |
-
from transformers.utils import logging
|
21 |
-
|
22 |
-
|
23 |
-
logger = logging.get_logger(__name__)
|
24 |
-
|
25 |
-
PHI3_PRETRAINED_CONFIG_ARCHIVE_MAP = {
|
26 |
-
"microsoft/Phi-3-mini-4k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/resolve/main/config.json",
|
27 |
-
"microsoft/Phi-3-mini-128k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/config.json",
|
28 |
-
}
|
29 |
-
|
30 |
-
|
31 |
-
class Phi3Config(PretrainedConfig):
|
32 |
-
r"""
|
33 |
-
This is the configuration class to store the configuration of a [`Phi3Model`]. It is used to instantiate a Phi-3
|
34 |
-
model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
|
35 |
-
defaults will yield a similar configuration to that of the
|
36 |
-
[microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct).
|
37 |
-
|
38 |
-
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
|
39 |
-
documentation from [`PretrainedConfig`] for more information.
|
40 |
-
|
41 |
-
Args:
|
42 |
-
vocab_size (`int`, *optional*, defaults to 32064):
|
43 |
-
Vocabulary size of the Phi-3 model. Defines the number of different tokens that can be represented by the
|
44 |
-
`inputs_ids` passed when calling [`Phi3Model`].
|
45 |
-
hidden_size (`int`, *optional*, defaults to 3072):
|
46 |
-
Dimension of the hidden representations.
|
47 |
-
intermediate_size (`int`, *optional*, defaults to 8192):
|
48 |
-
Dimension of the MLP representations.
|
49 |
-
num_hidden_layers (`int`, *optional*, defaults to 32):
|
50 |
-
Number of hidden layers in the Transformer decoder.
|
51 |
-
num_attention_heads (`int`, *optional*, defaults to 32):
|
52 |
-
Number of attention heads for each attention layer in the Transformer decoder.
|
53 |
-
num_key_value_heads (`int`, *optional*):
|
54 |
-
This is the number of key_value heads that should be used to implement Grouped Query Attention. If
|
55 |
-
`num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
|
56 |
-
`num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
|
57 |
-
converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
|
58 |
-
by meanpooling all the original heads within that group. For more details checkout [this
|
59 |
-
paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
|
60 |
-
`num_attention_heads`.
|
61 |
-
resid_pdrop (`float`, *optional*, defaults to 0.0):
|
62 |
-
Dropout probability for mlp outputs.
|
63 |
-
embd_pdrop (`int`, *optional*, defaults to 0.0):
|
64 |
-
The dropout ratio for the embeddings.
|
65 |
-
attention_dropout (`float`, *optional*, defaults to 0.0):
|
66 |
-
The dropout ratio after computing the attention scores.
|
67 |
-
hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
|
68 |
-
The non-linear activation function (function or string) in the decoder.
|
69 |
-
max_position_embeddings (`int`, *optional*, defaults to 4096):
|
70 |
-
The maximum sequence length that this model might ever be used with.
|
71 |
-
original_max_position_embeddings (`int`, *optional*, defaults to 4096):
|
72 |
-
The maximum sequence length that this model was trained with. This is used to determine the size of the
|
73 |
-
original RoPE embeddings when using long scaling.
|
74 |
-
initializer_range (`float`, *optional*, defaults to 0.02):
|
75 |
-
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
|
76 |
-
rms_norm_eps (`float`, *optional*, defaults to 1e-05):
|
77 |
-
The epsilon value used for the RMSNorm.
|
78 |
-
use_cache (`bool`, *optional*, defaults to `True`):
|
79 |
-
Whether or not the model should return the last key/values attentions (not used by all models). Only
|
80 |
-
relevant if `config.is_decoder=True`. Whether to tie weight embeddings or not.
|
81 |
-
tie_word_embeddings (`bool`, *optional*, defaults to `False`):
|
82 |
-
Whether to tie weight embeddings
|
83 |
-
rope_theta (`float`, *optional*, defaults to 10000.0):
|
84 |
-
The base period of the RoPE embeddings.
|
85 |
-
rope_scaling (`dict`, *optional*):
|
86 |
-
The scaling strategy for the RoPE embeddings. If `None`, no scaling is applied. If a dictionary, it must
|
87 |
-
contain the following keys: `type`, `short_factor` and `long_factor`. The `type` must be
|
88 |
-
the `short_factor` and `long_factor` must be lists of numbers with the same length as the hidden size
|
89 |
-
divided by the number of attention heads divided by 2.
|
90 |
-
bos_token_id (`int`, *optional*, defaults to 1):
|
91 |
-
The id of the "beginning-of-sequence" token.
|
92 |
-
eos_token_id (`int`, *optional*, defaults to 32000):
|
93 |
-
The id of the "end-of-sequence" token.
|
94 |
-
pad_token_id (`int`, *optional*, defaults to 32000):
|
95 |
-
The id of the padding token.
|
96 |
-
sliding_window (`int`, *optional*):
|
97 |
-
Sliding window attention window size. If `None`, no sliding window is applied.
|
98 |
-
|
99 |
-
Example:
|
100 |
-
|
101 |
-
```python
|
102 |
-
>>> from transformers import Phi3Model, Phi3Config
|
103 |
-
|
104 |
-
>>> # Initializing a Phi-3 style configuration
|
105 |
-
>>> configuration = Phi3Config.from_pretrained("microsoft/Phi-3-mini-4k-instruct")
|
106 |
-
|
107 |
-
>>> # Initializing a model from the configuration
|
108 |
-
>>> model = Phi3Model(configuration)
|
109 |
-
|
110 |
-
>>> # Accessing the model configuration
|
111 |
-
>>> configuration = model.config
|
112 |
-
```"""
|
113 |
-
|
114 |
-
model_type = "phi3"
|
115 |
-
keys_to_ignore_at_inference = ["past_key_values"]
|
116 |
-
|
117 |
-
def __init__(
|
118 |
-
self,
|
119 |
-
vocab_size=32064,
|
120 |
-
hidden_size=3072,
|
121 |
-
intermediate_size=8192,
|
122 |
-
num_hidden_layers=32,
|
123 |
-
num_attention_heads=32,
|
124 |
-
num_key_value_heads=None,
|
125 |
-
resid_pdrop=0.0,
|
126 |
-
embd_pdrop=0.0,
|
127 |
-
attention_dropout=0.0,
|
128 |
-
hidden_act="silu",
|
129 |
-
max_position_embeddings=4096,
|
130 |
-
original_max_position_embeddings=4096,
|
131 |
-
initializer_range=0.02,
|
132 |
-
rms_norm_eps=1e-5,
|
133 |
-
use_cache=True,
|
134 |
-
tie_word_embeddings=False,
|
135 |
-
rope_theta=10000.0,
|
136 |
-
rope_scaling=None,
|
137 |
-
bos_token_id=1,
|
138 |
-
eos_token_id=32000,
|
139 |
-
pad_token_id=32000,
|
140 |
-
sliding_window=None,
|
141 |
-
**kwargs,
|
142 |
-
):
|
143 |
-
self.vocab_size = vocab_size
|
144 |
-
self.hidden_size = hidden_size
|
145 |
-
self.intermediate_size = intermediate_size
|
146 |
-
self.num_hidden_layers = num_hidden_layers
|
147 |
-
self.num_attention_heads = num_attention_heads
|
148 |
-
|
149 |
-
if num_key_value_heads is None:
|
150 |
-
num_key_value_heads = num_attention_heads
|
151 |
-
|
152 |
-
self.num_key_value_heads = num_key_value_heads
|
153 |
-
self.resid_pdrop = resid_pdrop
|
154 |
-
self.embd_pdrop = embd_pdrop
|
155 |
-
self.attention_dropout = attention_dropout
|
156 |
-
self.hidden_act = hidden_act
|
157 |
-
self.max_position_embeddings = max_position_embeddings
|
158 |
-
self.original_max_position_embeddings = original_max_position_embeddings
|
159 |
-
self.initializer_range = initializer_range
|
160 |
-
self.rms_norm_eps = rms_norm_eps
|
161 |
-
self.use_cache = use_cache
|
162 |
-
self.rope_theta = rope_theta
|
163 |
-
self.rope_scaling = rope_scaling
|
164 |
-
self.
|
165 |
-
self.
|
166 |
-
|
167 |
-
|
168 |
-
|
169 |
-
|
170 |
-
|
171 |
-
|
172 |
-
|
173 |
-
|
174 |
-
|
175 |
-
|
176 |
-
|
177 |
-
|
178 |
-
|
179 |
-
|
180 |
-
|
181 |
-
|
182 |
-
|
183 |
-
|
184 |
-
|
185 |
-
|
186 |
-
|
187 |
-
|
188 |
-
|
189 |
-
|
190 |
-
|
191 |
-
|
192 |
-
|
193 |
-
|
194 |
-
|
195 |
-
|
196 |
-
|
197 |
-
|
198 |
-
|
199 |
-
|
200 |
-
|
201 |
-
|
202 |
-
|
203 |
-
|
204 |
-
|
205 |
-
|
206 |
-
|
207 |
-
|
208 |
-
|
209 |
-
|
210 |
-
|
211 |
-
|
212 |
-
|
213 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# coding=utf-8
|
2 |
+
# Copyright 2024 Microsoft and the HuggingFace Inc. team. All rights reserved.
|
3 |
+
#
|
4 |
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
5 |
+
# you may not use this file except in compliance with the License.
|
6 |
+
# You may obtain a copy of the License at
|
7 |
+
#
|
8 |
+
# http://www.apache.org/licenses/LICENSE-2.0
|
9 |
+
#
|
10 |
+
# Unless required by applicable law or agreed to in writing, software
|
11 |
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
12 |
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
13 |
+
# See the License for the specific language governing permissions and
|
14 |
+
# limitations under the License.
|
15 |
+
|
16 |
+
""" Phi-3 model configuration"""
|
17 |
+
|
18 |
+
|
19 |
+
from transformers.configuration_utils import PretrainedConfig
|
20 |
+
from transformers.utils import logging
|
21 |
+
|
22 |
+
|
23 |
+
logger = logging.get_logger(__name__)
|
24 |
+
|
25 |
+
PHI3_PRETRAINED_CONFIG_ARCHIVE_MAP = {
|
26 |
+
"microsoft/Phi-3-mini-4k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/resolve/main/config.json",
|
27 |
+
"microsoft/Phi-3-mini-128k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/config.json",
|
28 |
+
}
|
29 |
+
|
30 |
+
|
31 |
+
class Phi3Config(PretrainedConfig):
|
32 |
+
r"""
|
33 |
+
This is the configuration class to store the configuration of a [`Phi3Model`]. It is used to instantiate a Phi-3
|
34 |
+
model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
|
35 |
+
defaults will yield a similar configuration to that of the
|
36 |
+
[microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct).
|
37 |
+
|
38 |
+
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
|
39 |
+
documentation from [`PretrainedConfig`] for more information.
|
40 |
+
|
41 |
+
Args:
|
42 |
+
vocab_size (`int`, *optional*, defaults to 32064):
|
43 |
+
Vocabulary size of the Phi-3 model. Defines the number of different tokens that can be represented by the
|
44 |
+
`inputs_ids` passed when calling [`Phi3Model`].
|
45 |
+
hidden_size (`int`, *optional*, defaults to 3072):
|
46 |
+
Dimension of the hidden representations.
|
47 |
+
intermediate_size (`int`, *optional*, defaults to 8192):
|
48 |
+
Dimension of the MLP representations.
|
49 |
+
num_hidden_layers (`int`, *optional*, defaults to 32):
|
50 |
+
Number of hidden layers in the Transformer decoder.
|
51 |
+
num_attention_heads (`int`, *optional*, defaults to 32):
|
52 |
+
Number of attention heads for each attention layer in the Transformer decoder.
|
53 |
+
num_key_value_heads (`int`, *optional*):
|
54 |
+
This is the number of key_value heads that should be used to implement Grouped Query Attention. If
|
55 |
+
`num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
|
56 |
+
`num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
|
57 |
+
converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
|
58 |
+
by meanpooling all the original heads within that group. For more details checkout [this
|
59 |
+
paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
|
60 |
+
`num_attention_heads`.
|
61 |
+
resid_pdrop (`float`, *optional*, defaults to 0.0):
|
62 |
+
Dropout probability for mlp outputs.
|
63 |
+
embd_pdrop (`int`, *optional*, defaults to 0.0):
|
64 |
+
The dropout ratio for the embeddings.
|
65 |
+
attention_dropout (`float`, *optional*, defaults to 0.0):
|
66 |
+
The dropout ratio after computing the attention scores.
|
67 |
+
hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
|
68 |
+
The non-linear activation function (function or string) in the decoder.
|
69 |
+
max_position_embeddings (`int`, *optional*, defaults to 4096):
|
70 |
+
The maximum sequence length that this model might ever be used with.
|
71 |
+
original_max_position_embeddings (`int`, *optional*, defaults to 4096):
|
72 |
+
The maximum sequence length that this model was trained with. This is used to determine the size of the
|
73 |
+
original RoPE embeddings when using long scaling.
|
74 |
+
initializer_range (`float`, *optional*, defaults to 0.02):
|
75 |
+
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
|
76 |
+
rms_norm_eps (`float`, *optional*, defaults to 1e-05):
|
77 |
+
The epsilon value used for the RMSNorm.
|
78 |
+
use_cache (`bool`, *optional*, defaults to `True`):
|
79 |
+
Whether or not the model should return the last key/values attentions (not used by all models). Only
|
80 |
+
relevant if `config.is_decoder=True`. Whether to tie weight embeddings or not.
|
81 |
+
tie_word_embeddings (`bool`, *optional*, defaults to `False`):
|
82 |
+
Whether to tie weight embeddings
|
83 |
+
rope_theta (`float`, *optional*, defaults to 10000.0):
|
84 |
+
The base period of the RoPE embeddings.
|
85 |
+
rope_scaling (`dict`, *optional*):
|
86 |
+
The scaling strategy for the RoPE embeddings. If `None`, no scaling is applied. If a dictionary, it must
|
87 |
+
contain the following keys: `type`, `short_factor` and `long_factor`. The `type` must be `longrope` and
|
88 |
+
the `short_factor` and `long_factor` must be lists of numbers with the same length as the hidden size
|
89 |
+
divided by the number of attention heads divided by 2.
|
90 |
+
bos_token_id (`int`, *optional*, defaults to 1):
|
91 |
+
The id of the "beginning-of-sequence" token.
|
92 |
+
eos_token_id (`int`, *optional*, defaults to 32000):
|
93 |
+
The id of the "end-of-sequence" token.
|
94 |
+
pad_token_id (`int`, *optional*, defaults to 32000):
|
95 |
+
The id of the padding token.
|
96 |
+
sliding_window (`int`, *optional*):
|
97 |
+
Sliding window attention window size. If `None`, no sliding window is applied.
|
98 |
+
|
99 |
+
Example:
|
100 |
+
|
101 |
+
```python
|
102 |
+
>>> from transformers import Phi3Model, Phi3Config
|
103 |
+
|
104 |
+
>>> # Initializing a Phi-3 style configuration
|
105 |
+
>>> configuration = Phi3Config.from_pretrained("microsoft/Phi-3-mini-4k-instruct")
|
106 |
+
|
107 |
+
>>> # Initializing a model from the configuration
|
108 |
+
>>> model = Phi3Model(configuration)
|
109 |
+
|
110 |
+
>>> # Accessing the model configuration
|
111 |
+
>>> configuration = model.config
|
112 |
+
```"""
|
113 |
+
|
114 |
+
model_type = "phi3"
|
115 |
+
keys_to_ignore_at_inference = ["past_key_values"]
|
116 |
+
|
117 |
+
def __init__(
|
118 |
+
self,
|
119 |
+
vocab_size=32064,
|
120 |
+
hidden_size=3072,
|
121 |
+
intermediate_size=8192,
|
122 |
+
num_hidden_layers=32,
|
123 |
+
num_attention_heads=32,
|
124 |
+
num_key_value_heads=None,
|
125 |
+
resid_pdrop=0.0,
|
126 |
+
embd_pdrop=0.0,
|
127 |
+
attention_dropout=0.0,
|
128 |
+
hidden_act="silu",
|
129 |
+
max_position_embeddings=4096,
|
130 |
+
original_max_position_embeddings=4096,
|
131 |
+
initializer_range=0.02,
|
132 |
+
rms_norm_eps=1e-5,
|
133 |
+
use_cache=True,
|
134 |
+
tie_word_embeddings=False,
|
135 |
+
rope_theta=10000.0,
|
136 |
+
rope_scaling=None,
|
137 |
+
bos_token_id=1,
|
138 |
+
eos_token_id=32000,
|
139 |
+
pad_token_id=32000,
|
140 |
+
sliding_window=None,
|
141 |
+
**kwargs,
|
142 |
+
):
|
143 |
+
self.vocab_size = vocab_size
|
144 |
+
self.hidden_size = hidden_size
|
145 |
+
self.intermediate_size = intermediate_size
|
146 |
+
self.num_hidden_layers = num_hidden_layers
|
147 |
+
self.num_attention_heads = num_attention_heads
|
148 |
+
|
149 |
+
if num_key_value_heads is None:
|
150 |
+
num_key_value_heads = num_attention_heads
|
151 |
+
|
152 |
+
self.num_key_value_heads = num_key_value_heads
|
153 |
+
self.resid_pdrop = resid_pdrop
|
154 |
+
self.embd_pdrop = embd_pdrop
|
155 |
+
self.attention_dropout = attention_dropout
|
156 |
+
self.hidden_act = hidden_act
|
157 |
+
self.max_position_embeddings = max_position_embeddings
|
158 |
+
self.original_max_position_embeddings = original_max_position_embeddings
|
159 |
+
self.initializer_range = initializer_range
|
160 |
+
self.rms_norm_eps = rms_norm_eps
|
161 |
+
self.use_cache = use_cache
|
162 |
+
self.rope_theta = rope_theta
|
163 |
+
self.rope_scaling = rope_scaling
|
164 |
+
self._rope_scaling_adjustment()
|
165 |
+
self._rope_scaling_validation()
|
166 |
+
self.sliding_window = sliding_window
|
167 |
+
|
168 |
+
super().__init__(
|
169 |
+
bos_token_id=bos_token_id,
|
170 |
+
eos_token_id=eos_token_id,
|
171 |
+
pad_token_id=pad_token_id,
|
172 |
+
tie_word_embeddings=tie_word_embeddings,
|
173 |
+
**kwargs,
|
174 |
+
)
|
175 |
+
|
176 |
+
def _rope_scaling_adjustment(self):
|
177 |
+
"""
|
178 |
+
Adjust the `type` of the `rope_scaling` configuration for backward compatibility.
|
179 |
+
"""
|
180 |
+
if self.rope_scaling is None:
|
181 |
+
return
|
182 |
+
|
183 |
+
rope_scaling_type = self.rope_scaling.get("type", None)
|
184 |
+
|
185 |
+
# For backward compatibility if previous version used "su" or "yarn"
|
186 |
+
if rope_scaling_type is not None and rope_scaling_type in ["su", "yarn"]:
|
187 |
+
self.rope_scaling["type"] = "longrope"
|
188 |
+
|
189 |
+
def _rope_scaling_validation(self):
|
190 |
+
"""
|
191 |
+
Validate the `rope_scaling` configuration.
|
192 |
+
"""
|
193 |
+
if self.rope_scaling is None:
|
194 |
+
return
|
195 |
+
|
196 |
+
if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 3:
|
197 |
+
raise ValueError(
|
198 |
+
"`rope_scaling` must be a dictionary with three fields, `type`, `short_factor` and `long_factor`, "
|
199 |
+
f"got {self.rope_scaling}"
|
200 |
+
)
|
201 |
+
rope_scaling_type = self.rope_scaling.get("type", None)
|
202 |
+
rope_scaling_short_factor = self.rope_scaling.get("short_factor", None)
|
203 |
+
rope_scaling_long_factor = self.rope_scaling.get("long_factor", None)
|
204 |
+
if rope_scaling_type is None or rope_scaling_type not in ["longrope"]:
|
205 |
+
raise ValueError(f"`rope_scaling`'s type field must be one of ['longrope'], got {rope_scaling_type}")
|
206 |
+
if not (
|
207 |
+
isinstance(rope_scaling_short_factor, list)
|
208 |
+
and all(isinstance(x, (int, float)) for x in rope_scaling_short_factor)
|
209 |
+
):
|
210 |
+
raise ValueError(
|
211 |
+
f"`rope_scaling`'s short_factor field must be a list of numbers, got {rope_scaling_short_factor}"
|
212 |
+
)
|
213 |
+
if not len(rope_scaling_short_factor) == self.hidden_size // self.num_attention_heads // 2:
|
214 |
+
raise ValueError(
|
215 |
+
f"`rope_scaling`'s short_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_short_factor)}"
|
216 |
+
)
|
217 |
+
if not (
|
218 |
+
isinstance(rope_scaling_long_factor, list)
|
219 |
+
and all(isinstance(x, (int, float)) for x in rope_scaling_long_factor)
|
220 |
+
):
|
221 |
+
raise ValueError(
|
222 |
+
f"`rope_scaling`'s long_factor field must be a list of numbers, got {rope_scaling_long_factor}"
|
223 |
+
)
|
224 |
+
if not len(rope_scaling_long_factor) == self.hidden_size // self.num_attention_heads // 2:
|
225 |
+
raise ValueError(
|
226 |
+
f"`rope_scaling`'s long_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_long_factor)}"
|
227 |
+
)
|
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/phi3-mini-4k-instruct-cpu-int4-rtn-block-32-acc-level-4.onnx.data
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2722861056
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:798adddc78bdc16a877303e1ceb8938a3cbfe43459c9a6b735a35c9f9babb09c
|
3 |
size 2722861056
|
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/special_tokens_map.json
CHANGED
@@ -1,30 +1,30 @@
|
|
1 |
-
{
|
2 |
-
"bos_token": {
|
3 |
-
"content": "<s>",
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": false,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"eos_token": {
|
10 |
-
"content": "<|endoftext|>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"pad_token": {
|
17 |
-
"content": "<|endoftext|>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"unk_token": {
|
24 |
-
"content": "<unk>",
|
25 |
-
"lstrip": false,
|
26 |
-
"normalized": false,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
}
|
30 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/tokenizer_config.json
CHANGED
@@ -1,130 +1,130 @@
|
|
1 |
-
{
|
2 |
-
"add_bos_token":
|
3 |
-
"add_eos_token": false,
|
4 |
-
"added_tokens_decoder": {
|
5 |
-
"0": {
|
6 |
-
"content": "<unk>",
|
7 |
-
"lstrip": false,
|
8 |
-
"normalized": false,
|
9 |
-
"rstrip": false,
|
10 |
-
"single_word": false,
|
11 |
-
"special": true
|
12 |
-
},
|
13 |
-
"1": {
|
14 |
-
"content": "<s>",
|
15 |
-
"lstrip": false,
|
16 |
-
"normalized": false,
|
17 |
-
"rstrip": false,
|
18 |
-
"single_word": false,
|
19 |
-
"special": true
|
20 |
-
},
|
21 |
-
"2": {
|
22 |
-
"content": "</s>",
|
23 |
-
"lstrip": false,
|
24 |
-
"normalized": false,
|
25 |
-
"rstrip": true,
|
26 |
-
"single_word": false,
|
27 |
-
"special": false
|
28 |
-
},
|
29 |
-
"32000": {
|
30 |
-
"content": "<|endoftext|>",
|
31 |
-
"lstrip": false,
|
32 |
-
"normalized": false,
|
33 |
-
"rstrip": false,
|
34 |
-
"single_word": false,
|
35 |
-
"special": true
|
36 |
-
},
|
37 |
-
"32001": {
|
38 |
-
"content": "<|assistant|>",
|
39 |
-
"lstrip": false,
|
40 |
-
"normalized": false,
|
41 |
-
"rstrip": true,
|
42 |
-
"single_word": false,
|
43 |
-
"special": true
|
44 |
-
},
|
45 |
-
"32002": {
|
46 |
-
"content": "<|placeholder1|>",
|
47 |
-
"lstrip": false,
|
48 |
-
"normalized": false,
|
49 |
-
"rstrip": true,
|
50 |
-
"single_word": false,
|
51 |
-
"special": true
|
52 |
-
},
|
53 |
-
"32003": {
|
54 |
-
"content": "<|placeholder2|>",
|
55 |
-
"lstrip": false,
|
56 |
-
"normalized": false,
|
57 |
-
"rstrip": true,
|
58 |
-
"single_word": false,
|
59 |
-
"special": true
|
60 |
-
},
|
61 |
-
"32004": {
|
62 |
-
"content": "<|placeholder3|>",
|
63 |
-
"lstrip": false,
|
64 |
-
"normalized": false,
|
65 |
-
"rstrip": true,
|
66 |
-
"single_word": false,
|
67 |
-
"special": true
|
68 |
-
},
|
69 |
-
"32005": {
|
70 |
-
"content": "<|placeholder4|>",
|
71 |
-
"lstrip": false,
|
72 |
-
"normalized": false,
|
73 |
-
"rstrip": true,
|
74 |
-
"single_word": false,
|
75 |
-
"special": true
|
76 |
-
},
|
77 |
-
"32006": {
|
78 |
-
"content": "<|system|>",
|
79 |
-
"lstrip": false,
|
80 |
-
"normalized": false,
|
81 |
-
"rstrip": true,
|
82 |
-
"single_word": false,
|
83 |
-
"special": true
|
84 |
-
},
|
85 |
-
"32007": {
|
86 |
-
"content": "<|end|>",
|
87 |
-
"lstrip": false,
|
88 |
-
"normalized": false,
|
89 |
-
"rstrip": true,
|
90 |
-
"single_word": false,
|
91 |
-
"special": true
|
92 |
-
},
|
93 |
-
"32008": {
|
94 |
-
"content": "<|placeholder5|>",
|
95 |
-
"lstrip": false,
|
96 |
-
"normalized": false,
|
97 |
-
"rstrip": true,
|
98 |
-
"single_word": false,
|
99 |
-
"special": true
|
100 |
-
},
|
101 |
-
"32009": {
|
102 |
-
"content": "<|placeholder6|>",
|
103 |
-
"lstrip": false,
|
104 |
-
"normalized": false,
|
105 |
-
"rstrip": true,
|
106 |
-
"single_word": false,
|
107 |
-
"special": true
|
108 |
-
},
|
109 |
-
"32010": {
|
110 |
-
"content": "<|user|>",
|
111 |
-
"lstrip": false,
|
112 |
-
"normalized": false,
|
113 |
-
"rstrip": true,
|
114 |
-
"single_word": false,
|
115 |
-
"special": true
|
116 |
-
}
|
117 |
-
},
|
118 |
-
"bos_token": "<s>",
|
119 |
-
"chat_template": "{
|
120 |
-
"clean_up_tokenization_spaces": false,
|
121 |
-
"eos_token": "<|endoftext|>",
|
122 |
-
"legacy": false,
|
123 |
-
"model_max_length": 4096,
|
124 |
-
"pad_token": "<|endoftext|>",
|
125 |
-
"padding_side": "left",
|
126 |
-
"sp_model_kwargs": {},
|
127 |
-
"tokenizer_class": "LlamaTokenizer",
|
128 |
-
"unk_token": "<unk>",
|
129 |
-
"use_default_system_prompt": false
|
130 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": true,
|
26 |
+
"single_word": false,
|
27 |
+
"special": false
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "<|endoftext|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"32001": {
|
38 |
+
"content": "<|assistant|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": true,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"32002": {
|
46 |
+
"content": "<|placeholder1|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": true,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"32003": {
|
54 |
+
"content": "<|placeholder2|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": true,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"32004": {
|
62 |
+
"content": "<|placeholder3|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": true,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"32005": {
|
70 |
+
"content": "<|placeholder4|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": true,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"32006": {
|
78 |
+
"content": "<|system|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": true,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"32007": {
|
86 |
+
"content": "<|end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": true,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"32008": {
|
94 |
+
"content": "<|placeholder5|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": true,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"32009": {
|
102 |
+
"content": "<|placeholder6|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": true,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"32010": {
|
110 |
+
"content": "<|user|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": true,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
}
|
117 |
+
},
|
118 |
+
"bos_token": "<s>",
|
119 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
|
120 |
+
"clean_up_tokenization_spaces": false,
|
121 |
+
"eos_token": "<|endoftext|>",
|
122 |
+
"legacy": false,
|
123 |
+
"model_max_length": 4096,
|
124 |
+
"pad_token": "<|endoftext|>",
|
125 |
+
"padding_side": "left",
|
126 |
+
"sp_model_kwargs": {},
|
127 |
+
"tokenizer_class": "LlamaTokenizer",
|
128 |
+
"unk_token": "<unk>",
|
129 |
+
"use_default_system_prompt": false
|
130 |
+
}
|
cpu_and_mobile/cpu-int4-rtn-block-32/added_tokens.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
-
{
|
2 |
-
"<|endoftext|>": 32000,
|
3 |
-
"<|assistant|>": 32001,
|
4 |
-
"<|placeholder1|>": 32002,
|
5 |
-
"<|placeholder2|>": 32003,
|
6 |
-
"<|placeholder3|>": 32004,
|
7 |
-
"<|placeholder4|>": 32005,
|
8 |
-
"<|system|>": 32006,
|
9 |
-
"<|end|>": 32007,
|
10 |
-
"<|placeholder5|>": 32008,
|
11 |
-
"<|placeholder6|>": 32009,
|
12 |
-
"<|user|>": 32010
|
13 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 32000,
|
3 |
+
"<|assistant|>": 32001,
|
4 |
+
"<|placeholder1|>": 32002,
|
5 |
+
"<|placeholder2|>": 32003,
|
6 |
+
"<|placeholder3|>": 32004,
|
7 |
+
"<|placeholder4|>": 32005,
|
8 |
+
"<|system|>": 32006,
|
9 |
+
"<|end|>": 32007,
|
10 |
+
"<|placeholder5|>": 32008,
|
11 |
+
"<|placeholder6|>": 32009,
|
12 |
+
"<|user|>": 32010
|
13 |
+
}
|
cpu_and_mobile/cpu-int4-rtn-block-32/config.json
CHANGED
@@ -1,35 +1,36 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"architectures": [
|
4 |
-
"Phi3ForCausalLM"
|
5 |
-
],
|
6 |
-
"attention_dropout": 0.0,
|
7 |
-
"auto_map": {
|
8 |
-
"AutoConfig": "configuration_phi3.Phi3Config",
|
9 |
-
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
|
10 |
-
},
|
11 |
-
"bos_token_id": 1,
|
12 |
-
"embd_pdrop": 0.0,
|
13 |
-
"eos_token_id": 32000,
|
14 |
-
"hidden_act": "silu",
|
15 |
-
"hidden_size": 3072,
|
16 |
-
"initializer_range": 0.02,
|
17 |
-
"intermediate_size": 8192,
|
18 |
-
"max_position_embeddings": 4096,
|
19 |
-
"model_type": "phi3",
|
20 |
-
"num_attention_heads": 32,
|
21 |
-
"num_hidden_layers": 32,
|
22 |
-
"num_key_value_heads": 32,
|
23 |
-
"original_max_position_embeddings": 4096,
|
24 |
-
"pad_token_id": 32000,
|
25 |
-
"resid_pdrop": 0.0,
|
26 |
-
"rms_norm_eps": 1e-05,
|
27 |
-
"rope_scaling": null,
|
28 |
-
"rope_theta": 10000.0,
|
29 |
-
"sliding_window": 2047,
|
30 |
-
"tie_word_embeddings": false,
|
31 |
-
"torch_dtype": "bfloat16",
|
32 |
-
"transformers_version": "4.
|
33 |
-
"use_cache": true,
|
34 |
-
"
|
35 |
-
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Phi-3-mini-4k-instruct",
|
3 |
+
"architectures": [
|
4 |
+
"Phi3ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"auto_map": {
|
8 |
+
"AutoConfig": "configuration_phi3.Phi3Config",
|
9 |
+
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
|
10 |
+
},
|
11 |
+
"bos_token_id": 1,
|
12 |
+
"embd_pdrop": 0.0,
|
13 |
+
"eos_token_id": 32000,
|
14 |
+
"hidden_act": "silu",
|
15 |
+
"hidden_size": 3072,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 8192,
|
18 |
+
"max_position_embeddings": 4096,
|
19 |
+
"model_type": "phi3",
|
20 |
+
"num_attention_heads": 32,
|
21 |
+
"num_hidden_layers": 32,
|
22 |
+
"num_key_value_heads": 32,
|
23 |
+
"original_max_position_embeddings": 4096,
|
24 |
+
"pad_token_id": 32000,
|
25 |
+
"resid_pdrop": 0.0,
|
26 |
+
"rms_norm_eps": 1e-05,
|
27 |
+
"rope_scaling": null,
|
28 |
+
"rope_theta": 10000.0,
|
29 |
+
"sliding_window": 2047,
|
30 |
+
"tie_word_embeddings": false,
|
31 |
+
"torch_dtype": "bfloat16",
|
32 |
+
"transformers_version": "4.40.2",
|
33 |
+
"use_cache": true,
|
34 |
+
"attention_bias": false,
|
35 |
+
"vocab_size": 32064
|
36 |
+
}
|
cpu_and_mobile/cpu-int4-rtn-block-32/configuration_phi3.py
CHANGED
@@ -1,213 +1,227 @@
|
|
1 |
-
# coding=utf-8
|
2 |
-
# Copyright 2024 Microsoft and the HuggingFace Inc. team. All rights reserved.
|
3 |
-
#
|
4 |
-
# Licensed under the Apache License, Version 2.0 (the "License");
|
5 |
-
# you may not use this file except in compliance with the License.
|
6 |
-
# You may obtain a copy of the License at
|
7 |
-
#
|
8 |
-
# http://www.apache.org/licenses/LICENSE-2.0
|
9 |
-
#
|
10 |
-
# Unless required by applicable law or agreed to in writing, software
|
11 |
-
# distributed under the License is distributed on an "AS IS" BASIS,
|
12 |
-
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
13 |
-
# See the License for the specific language governing permissions and
|
14 |
-
# limitations under the License.
|
15 |
-
|
16 |
-
""" Phi-3 model configuration"""
|
17 |
-
|
18 |
-
|
19 |
-
from transformers.configuration_utils import PretrainedConfig
|
20 |
-
from transformers.utils import logging
|
21 |
-
|
22 |
-
|
23 |
-
logger = logging.get_logger(__name__)
|
24 |
-
|
25 |
-
PHI3_PRETRAINED_CONFIG_ARCHIVE_MAP = {
|
26 |
-
"microsoft/Phi-3-mini-4k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/resolve/main/config.json",
|
27 |
-
"microsoft/Phi-3-mini-128k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/config.json",
|
28 |
-
}
|
29 |
-
|
30 |
-
|
31 |
-
class Phi3Config(PretrainedConfig):
|
32 |
-
r"""
|
33 |
-
This is the configuration class to store the configuration of a [`Phi3Model`]. It is used to instantiate a Phi-3
|
34 |
-
model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
|
35 |
-
defaults will yield a similar configuration to that of the
|
36 |
-
[microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct).
|
37 |
-
|
38 |
-
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
|
39 |
-
documentation from [`PretrainedConfig`] for more information.
|
40 |
-
|
41 |
-
Args:
|
42 |
-
vocab_size (`int`, *optional*, defaults to 32064):
|
43 |
-
Vocabulary size of the Phi-3 model. Defines the number of different tokens that can be represented by the
|
44 |
-
`inputs_ids` passed when calling [`Phi3Model`].
|
45 |
-
hidden_size (`int`, *optional*, defaults to 3072):
|
46 |
-
Dimension of the hidden representations.
|
47 |
-
intermediate_size (`int`, *optional*, defaults to 8192):
|
48 |
-
Dimension of the MLP representations.
|
49 |
-
num_hidden_layers (`int`, *optional*, defaults to 32):
|
50 |
-
Number of hidden layers in the Transformer decoder.
|
51 |
-
num_attention_heads (`int`, *optional*, defaults to 32):
|
52 |
-
Number of attention heads for each attention layer in the Transformer decoder.
|
53 |
-
num_key_value_heads (`int`, *optional*):
|
54 |
-
This is the number of key_value heads that should be used to implement Grouped Query Attention. If
|
55 |
-
`num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
|
56 |
-
`num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
|
57 |
-
converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
|
58 |
-
by meanpooling all the original heads within that group. For more details checkout [this
|
59 |
-
paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
|
60 |
-
`num_attention_heads`.
|
61 |
-
resid_pdrop (`float`, *optional*, defaults to 0.0):
|
62 |
-
Dropout probability for mlp outputs.
|
63 |
-
embd_pdrop (`int`, *optional*, defaults to 0.0):
|
64 |
-
The dropout ratio for the embeddings.
|
65 |
-
attention_dropout (`float`, *optional*, defaults to 0.0):
|
66 |
-
The dropout ratio after computing the attention scores.
|
67 |
-
hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
|
68 |
-
The non-linear activation function (function or string) in the decoder.
|
69 |
-
max_position_embeddings (`int`, *optional*, defaults to 4096):
|
70 |
-
The maximum sequence length that this model might ever be used with.
|
71 |
-
original_max_position_embeddings (`int`, *optional*, defaults to 4096):
|
72 |
-
The maximum sequence length that this model was trained with. This is used to determine the size of the
|
73 |
-
original RoPE embeddings when using long scaling.
|
74 |
-
initializer_range (`float`, *optional*, defaults to 0.02):
|
75 |
-
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
|
76 |
-
rms_norm_eps (`float`, *optional*, defaults to 1e-05):
|
77 |
-
The epsilon value used for the RMSNorm.
|
78 |
-
use_cache (`bool`, *optional*, defaults to `True`):
|
79 |
-
Whether or not the model should return the last key/values attentions (not used by all models). Only
|
80 |
-
relevant if `config.is_decoder=True`. Whether to tie weight embeddings or not.
|
81 |
-
tie_word_embeddings (`bool`, *optional*, defaults to `False`):
|
82 |
-
Whether to tie weight embeddings
|
83 |
-
rope_theta (`float`, *optional*, defaults to 10000.0):
|
84 |
-
The base period of the RoPE embeddings.
|
85 |
-
rope_scaling (`dict`, *optional*):
|
86 |
-
The scaling strategy for the RoPE embeddings. If `None`, no scaling is applied. If a dictionary, it must
|
87 |
-
contain the following keys: `type`, `short_factor` and `long_factor`. The `type` must be
|
88 |
-
the `short_factor` and `long_factor` must be lists of numbers with the same length as the hidden size
|
89 |
-
divided by the number of attention heads divided by 2.
|
90 |
-
bos_token_id (`int`, *optional*, defaults to 1):
|
91 |
-
The id of the "beginning-of-sequence" token.
|
92 |
-
eos_token_id (`int`, *optional*, defaults to 32000):
|
93 |
-
The id of the "end-of-sequence" token.
|
94 |
-
pad_token_id (`int`, *optional*, defaults to 32000):
|
95 |
-
The id of the padding token.
|
96 |
-
sliding_window (`int`, *optional*):
|
97 |
-
Sliding window attention window size. If `None`, no sliding window is applied.
|
98 |
-
|
99 |
-
Example:
|
100 |
-
|
101 |
-
```python
|
102 |
-
>>> from transformers import Phi3Model, Phi3Config
|
103 |
-
|
104 |
-
>>> # Initializing a Phi-3 style configuration
|
105 |
-
>>> configuration = Phi3Config.from_pretrained("microsoft/Phi-3-mini-4k-instruct")
|
106 |
-
|
107 |
-
>>> # Initializing a model from the configuration
|
108 |
-
>>> model = Phi3Model(configuration)
|
109 |
-
|
110 |
-
>>> # Accessing the model configuration
|
111 |
-
>>> configuration = model.config
|
112 |
-
```"""
|
113 |
-
|
114 |
-
model_type = "phi3"
|
115 |
-
keys_to_ignore_at_inference = ["past_key_values"]
|
116 |
-
|
117 |
-
def __init__(
|
118 |
-
self,
|
119 |
-
vocab_size=32064,
|
120 |
-
hidden_size=3072,
|
121 |
-
intermediate_size=8192,
|
122 |
-
num_hidden_layers=32,
|
123 |
-
num_attention_heads=32,
|
124 |
-
num_key_value_heads=None,
|
125 |
-
resid_pdrop=0.0,
|
126 |
-
embd_pdrop=0.0,
|
127 |
-
attention_dropout=0.0,
|
128 |
-
hidden_act="silu",
|
129 |
-
max_position_embeddings=4096,
|
130 |
-
original_max_position_embeddings=4096,
|
131 |
-
initializer_range=0.02,
|
132 |
-
rms_norm_eps=1e-5,
|
133 |
-
use_cache=True,
|
134 |
-
tie_word_embeddings=False,
|
135 |
-
rope_theta=10000.0,
|
136 |
-
rope_scaling=None,
|
137 |
-
bos_token_id=1,
|
138 |
-
eos_token_id=32000,
|
139 |
-
pad_token_id=32000,
|
140 |
-
sliding_window=None,
|
141 |
-
**kwargs,
|
142 |
-
):
|
143 |
-
self.vocab_size = vocab_size
|
144 |
-
self.hidden_size = hidden_size
|
145 |
-
self.intermediate_size = intermediate_size
|
146 |
-
self.num_hidden_layers = num_hidden_layers
|
147 |
-
self.num_attention_heads = num_attention_heads
|
148 |
-
|
149 |
-
if num_key_value_heads is None:
|
150 |
-
num_key_value_heads = num_attention_heads
|
151 |
-
|
152 |
-
self.num_key_value_heads = num_key_value_heads
|
153 |
-
self.resid_pdrop = resid_pdrop
|
154 |
-
self.embd_pdrop = embd_pdrop
|
155 |
-
self.attention_dropout = attention_dropout
|
156 |
-
self.hidden_act = hidden_act
|
157 |
-
self.max_position_embeddings = max_position_embeddings
|
158 |
-
self.original_max_position_embeddings = original_max_position_embeddings
|
159 |
-
self.initializer_range = initializer_range
|
160 |
-
self.rms_norm_eps = rms_norm_eps
|
161 |
-
self.use_cache = use_cache
|
162 |
-
self.rope_theta = rope_theta
|
163 |
-
self.rope_scaling = rope_scaling
|
164 |
-
self.
|
165 |
-
self.
|
166 |
-
|
167 |
-
|
168 |
-
|
169 |
-
|
170 |
-
|
171 |
-
|
172 |
-
|
173 |
-
|
174 |
-
|
175 |
-
|
176 |
-
|
177 |
-
|
178 |
-
|
179 |
-
|
180 |
-
|
181 |
-
|
182 |
-
|
183 |
-
|
184 |
-
|
185 |
-
|
186 |
-
|
187 |
-
|
188 |
-
|
189 |
-
|
190 |
-
|
191 |
-
|
192 |
-
|
193 |
-
|
194 |
-
|
195 |
-
|
196 |
-
|
197 |
-
|
198 |
-
|
199 |
-
|
200 |
-
|
201 |
-
|
202 |
-
|
203 |
-
|
204 |
-
|
205 |
-
|
206 |
-
|
207 |
-
|
208 |
-
|
209 |
-
|
210 |
-
|
211 |
-
|
212 |
-
|
213 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# coding=utf-8
|
2 |
+
# Copyright 2024 Microsoft and the HuggingFace Inc. team. All rights reserved.
|
3 |
+
#
|
4 |
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
5 |
+
# you may not use this file except in compliance with the License.
|
6 |
+
# You may obtain a copy of the License at
|
7 |
+
#
|
8 |
+
# http://www.apache.org/licenses/LICENSE-2.0
|
9 |
+
#
|
10 |
+
# Unless required by applicable law or agreed to in writing, software
|
11 |
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
12 |
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
13 |
+
# See the License for the specific language governing permissions and
|
14 |
+
# limitations under the License.
|
15 |
+
|
16 |
+
""" Phi-3 model configuration"""
|
17 |
+
|
18 |
+
|
19 |
+
from transformers.configuration_utils import PretrainedConfig
|
20 |
+
from transformers.utils import logging
|
21 |
+
|
22 |
+
|
23 |
+
logger = logging.get_logger(__name__)
|
24 |
+
|
25 |
+
PHI3_PRETRAINED_CONFIG_ARCHIVE_MAP = {
|
26 |
+
"microsoft/Phi-3-mini-4k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/resolve/main/config.json",
|
27 |
+
"microsoft/Phi-3-mini-128k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/config.json",
|
28 |
+
}
|
29 |
+
|
30 |
+
|
31 |
+
class Phi3Config(PretrainedConfig):
|
32 |
+
r"""
|
33 |
+
This is the configuration class to store the configuration of a [`Phi3Model`]. It is used to instantiate a Phi-3
|
34 |
+
model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
|
35 |
+
defaults will yield a similar configuration to that of the
|
36 |
+
[microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct).
|
37 |
+
|
38 |
+
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
|
39 |
+
documentation from [`PretrainedConfig`] for more information.
|
40 |
+
|
41 |
+
Args:
|
42 |
+
vocab_size (`int`, *optional*, defaults to 32064):
|
43 |
+
Vocabulary size of the Phi-3 model. Defines the number of different tokens that can be represented by the
|
44 |
+
`inputs_ids` passed when calling [`Phi3Model`].
|
45 |
+
hidden_size (`int`, *optional*, defaults to 3072):
|
46 |
+
Dimension of the hidden representations.
|
47 |
+
intermediate_size (`int`, *optional*, defaults to 8192):
|
48 |
+
Dimension of the MLP representations.
|
49 |
+
num_hidden_layers (`int`, *optional*, defaults to 32):
|
50 |
+
Number of hidden layers in the Transformer decoder.
|
51 |
+
num_attention_heads (`int`, *optional*, defaults to 32):
|
52 |
+
Number of attention heads for each attention layer in the Transformer decoder.
|
53 |
+
num_key_value_heads (`int`, *optional*):
|
54 |
+
This is the number of key_value heads that should be used to implement Grouped Query Attention. If
|
55 |
+
`num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
|
56 |
+
`num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
|
57 |
+
converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
|
58 |
+
by meanpooling all the original heads within that group. For more details checkout [this
|
59 |
+
paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
|
60 |
+
`num_attention_heads`.
|
61 |
+
resid_pdrop (`float`, *optional*, defaults to 0.0):
|
62 |
+
Dropout probability for mlp outputs.
|
63 |
+
embd_pdrop (`int`, *optional*, defaults to 0.0):
|
64 |
+
The dropout ratio for the embeddings.
|
65 |
+
attention_dropout (`float`, *optional*, defaults to 0.0):
|
66 |
+
The dropout ratio after computing the attention scores.
|
67 |
+
hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
|
68 |
+
The non-linear activation function (function or string) in the decoder.
|
69 |
+
max_position_embeddings (`int`, *optional*, defaults to 4096):
|
70 |
+
The maximum sequence length that this model might ever be used with.
|
71 |
+
original_max_position_embeddings (`int`, *optional*, defaults to 4096):
|
72 |
+
The maximum sequence length that this model was trained with. This is used to determine the size of the
|
73 |
+
original RoPE embeddings when using long scaling.
|
74 |
+
initializer_range (`float`, *optional*, defaults to 0.02):
|
75 |
+
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
|
76 |
+
rms_norm_eps (`float`, *optional*, defaults to 1e-05):
|
77 |
+
The epsilon value used for the RMSNorm.
|
78 |
+
use_cache (`bool`, *optional*, defaults to `True`):
|
79 |
+
Whether or not the model should return the last key/values attentions (not used by all models). Only
|
80 |
+
relevant if `config.is_decoder=True`. Whether to tie weight embeddings or not.
|
81 |
+
tie_word_embeddings (`bool`, *optional*, defaults to `False`):
|
82 |
+
Whether to tie weight embeddings
|
83 |
+
rope_theta (`float`, *optional*, defaults to 10000.0):
|
84 |
+
The base period of the RoPE embeddings.
|
85 |
+
rope_scaling (`dict`, *optional*):
|
86 |
+
The scaling strategy for the RoPE embeddings. If `None`, no scaling is applied. If a dictionary, it must
|
87 |
+
contain the following keys: `type`, `short_factor` and `long_factor`. The `type` must be `longrope` and
|
88 |
+
the `short_factor` and `long_factor` must be lists of numbers with the same length as the hidden size
|
89 |
+
divided by the number of attention heads divided by 2.
|
90 |
+
bos_token_id (`int`, *optional*, defaults to 1):
|
91 |
+
The id of the "beginning-of-sequence" token.
|
92 |
+
eos_token_id (`int`, *optional*, defaults to 32000):
|
93 |
+
The id of the "end-of-sequence" token.
|
94 |
+
pad_token_id (`int`, *optional*, defaults to 32000):
|
95 |
+
The id of the padding token.
|
96 |
+
sliding_window (`int`, *optional*):
|
97 |
+
Sliding window attention window size. If `None`, no sliding window is applied.
|
98 |
+
|
99 |
+
Example:
|
100 |
+
|
101 |
+
```python
|
102 |
+
>>> from transformers import Phi3Model, Phi3Config
|
103 |
+
|
104 |
+
>>> # Initializing a Phi-3 style configuration
|
105 |
+
>>> configuration = Phi3Config.from_pretrained("microsoft/Phi-3-mini-4k-instruct")
|
106 |
+
|
107 |
+
>>> # Initializing a model from the configuration
|
108 |
+
>>> model = Phi3Model(configuration)
|
109 |
+
|
110 |
+
>>> # Accessing the model configuration
|
111 |
+
>>> configuration = model.config
|
112 |
+
```"""
|
113 |
+
|
114 |
+
model_type = "phi3"
|
115 |
+
keys_to_ignore_at_inference = ["past_key_values"]
|
116 |
+
|
117 |
+
def __init__(
|
118 |
+
self,
|
119 |
+
vocab_size=32064,
|
120 |
+
hidden_size=3072,
|
121 |
+
intermediate_size=8192,
|
122 |
+
num_hidden_layers=32,
|
123 |
+
num_attention_heads=32,
|
124 |
+
num_key_value_heads=None,
|
125 |
+
resid_pdrop=0.0,
|
126 |
+
embd_pdrop=0.0,
|
127 |
+
attention_dropout=0.0,
|
128 |
+
hidden_act="silu",
|
129 |
+
max_position_embeddings=4096,
|
130 |
+
original_max_position_embeddings=4096,
|
131 |
+
initializer_range=0.02,
|
132 |
+
rms_norm_eps=1e-5,
|
133 |
+
use_cache=True,
|
134 |
+
tie_word_embeddings=False,
|
135 |
+
rope_theta=10000.0,
|
136 |
+
rope_scaling=None,
|
137 |
+
bos_token_id=1,
|
138 |
+
eos_token_id=32000,
|
139 |
+
pad_token_id=32000,
|
140 |
+
sliding_window=None,
|
141 |
+
**kwargs,
|
142 |
+
):
|
143 |
+
self.vocab_size = vocab_size
|
144 |
+
self.hidden_size = hidden_size
|
145 |
+
self.intermediate_size = intermediate_size
|
146 |
+
self.num_hidden_layers = num_hidden_layers
|
147 |
+
self.num_attention_heads = num_attention_heads
|
148 |
+
|
149 |
+
if num_key_value_heads is None:
|
150 |
+
num_key_value_heads = num_attention_heads
|
151 |
+
|
152 |
+
self.num_key_value_heads = num_key_value_heads
|
153 |
+
self.resid_pdrop = resid_pdrop
|
154 |
+
self.embd_pdrop = embd_pdrop
|
155 |
+
self.attention_dropout = attention_dropout
|
156 |
+
self.hidden_act = hidden_act
|
157 |
+
self.max_position_embeddings = max_position_embeddings
|
158 |
+
self.original_max_position_embeddings = original_max_position_embeddings
|
159 |
+
self.initializer_range = initializer_range
|
160 |
+
self.rms_norm_eps = rms_norm_eps
|
161 |
+
self.use_cache = use_cache
|
162 |
+
self.rope_theta = rope_theta
|
163 |
+
self.rope_scaling = rope_scaling
|
164 |
+
self._rope_scaling_adjustment()
|
165 |
+
self._rope_scaling_validation()
|
166 |
+
self.sliding_window = sliding_window
|
167 |
+
|
168 |
+
super().__init__(
|
169 |
+
bos_token_id=bos_token_id,
|
170 |
+
eos_token_id=eos_token_id,
|
171 |
+
pad_token_id=pad_token_id,
|
172 |
+
tie_word_embeddings=tie_word_embeddings,
|
173 |
+
**kwargs,
|
174 |
+
)
|
175 |
+
|
176 |
+
def _rope_scaling_adjustment(self):
|
177 |
+
"""
|
178 |
+
Adjust the `type` of the `rope_scaling` configuration for backward compatibility.
|
179 |
+
"""
|
180 |
+
if self.rope_scaling is None:
|
181 |
+
return
|
182 |
+
|
183 |
+
rope_scaling_type = self.rope_scaling.get("type", None)
|
184 |
+
|
185 |
+
# For backward compatibility if previous version used "su" or "yarn"
|
186 |
+
if rope_scaling_type is not None and rope_scaling_type in ["su", "yarn"]:
|
187 |
+
self.rope_scaling["type"] = "longrope"
|
188 |
+
|
189 |
+
def _rope_scaling_validation(self):
|
190 |
+
"""
|
191 |
+
Validate the `rope_scaling` configuration.
|
192 |
+
"""
|
193 |
+
if self.rope_scaling is None:
|
194 |
+
return
|
195 |
+
|
196 |
+
if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 3:
|
197 |
+
raise ValueError(
|
198 |
+
"`rope_scaling` must be a dictionary with three fields, `type`, `short_factor` and `long_factor`, "
|
199 |
+
f"got {self.rope_scaling}"
|
200 |
+
)
|
201 |
+
rope_scaling_type = self.rope_scaling.get("type", None)
|
202 |
+
rope_scaling_short_factor = self.rope_scaling.get("short_factor", None)
|
203 |
+
rope_scaling_long_factor = self.rope_scaling.get("long_factor", None)
|
204 |
+
if rope_scaling_type is None or rope_scaling_type not in ["longrope"]:
|
205 |
+
raise ValueError(f"`rope_scaling`'s type field must be one of ['longrope'], got {rope_scaling_type}")
|
206 |
+
if not (
|
207 |
+
isinstance(rope_scaling_short_factor, list)
|
208 |
+
and all(isinstance(x, (int, float)) for x in rope_scaling_short_factor)
|
209 |
+
):
|
210 |
+
raise ValueError(
|
211 |
+
f"`rope_scaling`'s short_factor field must be a list of numbers, got {rope_scaling_short_factor}"
|
212 |
+
)
|
213 |
+
if not len(rope_scaling_short_factor) == self.hidden_size // self.num_attention_heads // 2:
|
214 |
+
raise ValueError(
|
215 |
+
f"`rope_scaling`'s short_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_short_factor)}"
|
216 |
+
)
|
217 |
+
if not (
|
218 |
+
isinstance(rope_scaling_long_factor, list)
|
219 |
+
and all(isinstance(x, (int, float)) for x in rope_scaling_long_factor)
|
220 |
+
):
|
221 |
+
raise ValueError(
|
222 |
+
f"`rope_scaling`'s long_factor field must be a list of numbers, got {rope_scaling_long_factor}"
|
223 |
+
)
|
224 |
+
if not len(rope_scaling_long_factor) == self.hidden_size // self.num_attention_heads // 2:
|
225 |
+
raise ValueError(
|
226 |
+
f"`rope_scaling`'s long_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_long_factor)}"
|
227 |
+
)
|
cpu_and_mobile/cpu-int4-rtn-block-32/phi3-mini-4k-instruct-cpu-int4-rtn-block-32.onnx.data
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2722861056
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:798adddc78bdc16a877303e1ceb8938a3cbfe43459c9a6b735a35c9f9babb09c
|
3 |
size 2722861056
|
cpu_and_mobile/cpu-int4-rtn-block-32/special_tokens_map.json
CHANGED
@@ -1,30 +1,30 @@
|
|
1 |
-
{
|
2 |
-
"bos_token": {
|
3 |
-
"content": "<s>",
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": false,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"eos_token": {
|
10 |
-
"content": "<|endoftext|>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"pad_token": {
|
17 |
-
"content": "<|endoftext|>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"unk_token": {
|
24 |
-
"content": "<unk>",
|
25 |
-
"lstrip": false,
|
26 |
-
"normalized": false,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
}
|
30 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
cpu_and_mobile/cpu-int4-rtn-block-32/tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
cpu_and_mobile/cpu-int4-rtn-block-32/tokenizer_config.json
CHANGED
@@ -1,130 +1,130 @@
|
|
1 |
-
{
|
2 |
-
"add_bos_token":
|
3 |
-
"add_eos_token": false,
|
4 |
-
"added_tokens_decoder": {
|
5 |
-
"0": {
|
6 |
-
"content": "<unk>",
|
7 |
-
"lstrip": false,
|
8 |
-
"normalized": false,
|
9 |
-
"rstrip": false,
|
10 |
-
"single_word": false,
|
11 |
-
"special": true
|
12 |
-
},
|
13 |
-
"1": {
|
14 |
-
"content": "<s>",
|
15 |
-
"lstrip": false,
|
16 |
-
"normalized": false,
|
17 |
-
"rstrip": false,
|
18 |
-
"single_word": false,
|
19 |
-
"special": true
|
20 |
-
},
|
21 |
-
"2": {
|
22 |
-
"content": "</s>",
|
23 |
-
"lstrip": false,
|
24 |
-
"normalized": false,
|
25 |
-
"rstrip": true,
|
26 |
-
"single_word": false,
|
27 |
-
"special": false
|
28 |
-
},
|
29 |
-
"32000": {
|
30 |
-
"content": "<|endoftext|>",
|
31 |
-
"lstrip": false,
|
32 |
-
"normalized": false,
|
33 |
-
"rstrip": false,
|
34 |
-
"single_word": false,
|
35 |
-
"special": true
|
36 |
-
},
|
37 |
-
"32001": {
|
38 |
-
"content": "<|assistant|>",
|
39 |
-
"lstrip": false,
|
40 |
-
"normalized": false,
|
41 |
-
"rstrip": true,
|
42 |
-
"single_word": false,
|
43 |
-
"special": true
|
44 |
-
},
|
45 |
-
"32002": {
|
46 |
-
"content": "<|placeholder1|>",
|
47 |
-
"lstrip": false,
|
48 |
-
"normalized": false,
|
49 |
-
"rstrip": true,
|
50 |
-
"single_word": false,
|
51 |
-
"special": true
|
52 |
-
},
|
53 |
-
"32003": {
|
54 |
-
"content": "<|placeholder2|>",
|
55 |
-
"lstrip": false,
|
56 |
-
"normalized": false,
|
57 |
-
"rstrip": true,
|
58 |
-
"single_word": false,
|
59 |
-
"special": true
|
60 |
-
},
|
61 |
-
"32004": {
|
62 |
-
"content": "<|placeholder3|>",
|
63 |
-
"lstrip": false,
|
64 |
-
"normalized": false,
|
65 |
-
"rstrip": true,
|
66 |
-
"single_word": false,
|
67 |
-
"special": true
|
68 |
-
},
|
69 |
-
"32005": {
|
70 |
-
"content": "<|placeholder4|>",
|
71 |
-
"lstrip": false,
|
72 |
-
"normalized": false,
|
73 |
-
"rstrip": true,
|
74 |
-
"single_word": false,
|
75 |
-
"special": true
|
76 |
-
},
|
77 |
-
"32006": {
|
78 |
-
"content": "<|system|>",
|
79 |
-
"lstrip": false,
|
80 |
-
"normalized": false,
|
81 |
-
"rstrip": true,
|
82 |
-
"single_word": false,
|
83 |
-
"special": true
|
84 |
-
},
|
85 |
-
"32007": {
|
86 |
-
"content": "<|end|>",
|
87 |
-
"lstrip": false,
|
88 |
-
"normalized": false,
|
89 |
-
"rstrip": true,
|
90 |
-
"single_word": false,
|
91 |
-
"special": true
|
92 |
-
},
|
93 |
-
"32008": {
|
94 |
-
"content": "<|placeholder5|>",
|
95 |
-
"lstrip": false,
|
96 |
-
"normalized": false,
|
97 |
-
"rstrip": true,
|
98 |
-
"single_word": false,
|
99 |
-
"special": true
|
100 |
-
},
|
101 |
-
"32009": {
|
102 |
-
"content": "<|placeholder6|>",
|
103 |
-
"lstrip": false,
|
104 |
-
"normalized": false,
|
105 |
-
"rstrip": true,
|
106 |
-
"single_word": false,
|
107 |
-
"special": true
|
108 |
-
},
|
109 |
-
"32010": {
|
110 |
-
"content": "<|user|>",
|
111 |
-
"lstrip": false,
|
112 |
-
"normalized": false,
|
113 |
-
"rstrip": true,
|
114 |
-
"single_word": false,
|
115 |
-
"special": true
|
116 |
-
}
|
117 |
-
},
|
118 |
-
"bos_token": "<s>",
|
119 |
-
"chat_template": "{
|
120 |
-
"clean_up_tokenization_spaces": false,
|
121 |
-
"eos_token": "<|endoftext|>",
|
122 |
-
"legacy": false,
|
123 |
-
"model_max_length": 4096,
|
124 |
-
"pad_token": "<|endoftext|>",
|
125 |
-
"padding_side": "left",
|
126 |
-
"sp_model_kwargs": {},
|
127 |
-
"tokenizer_class": "LlamaTokenizer",
|
128 |
-
"unk_token": "<unk>",
|
129 |
-
"use_default_system_prompt": false
|
130 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": true,
|
26 |
+
"single_word": false,
|
27 |
+
"special": false
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "<|endoftext|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"32001": {
|
38 |
+
"content": "<|assistant|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": true,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"32002": {
|
46 |
+
"content": "<|placeholder1|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": true,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"32003": {
|
54 |
+
"content": "<|placeholder2|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": true,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"32004": {
|
62 |
+
"content": "<|placeholder3|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": true,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"32005": {
|
70 |
+
"content": "<|placeholder4|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": true,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"32006": {
|
78 |
+
"content": "<|system|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": true,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"32007": {
|
86 |
+
"content": "<|end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": true,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"32008": {
|
94 |
+
"content": "<|placeholder5|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": true,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"32009": {
|
102 |
+
"content": "<|placeholder6|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": true,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"32010": {
|
110 |
+
"content": "<|user|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": true,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
}
|
117 |
+
},
|
118 |
+
"bos_token": "<s>",
|
119 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
|
120 |
+
"clean_up_tokenization_spaces": false,
|
121 |
+
"eos_token": "<|endoftext|>",
|
122 |
+
"legacy": false,
|
123 |
+
"model_max_length": 4096,
|
124 |
+
"pad_token": "<|endoftext|>",
|
125 |
+
"padding_side": "left",
|
126 |
+
"sp_model_kwargs": {},
|
127 |
+
"tokenizer_class": "LlamaTokenizer",
|
128 |
+
"unk_token": "<unk>",
|
129 |
+
"use_default_system_prompt": false
|
130 |
+
}
|
cuda/cuda-fp16/added_tokens.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
-
{
|
2 |
-
"<|endoftext|>": 32000,
|
3 |
-
"<|assistant|>": 32001,
|
4 |
-
"<|placeholder1|>": 32002,
|
5 |
-
"<|placeholder2|>": 32003,
|
6 |
-
"<|placeholder3|>": 32004,
|
7 |
-
"<|placeholder4|>": 32005,
|
8 |
-
"<|system|>": 32006,
|
9 |
-
"<|end|>": 32007,
|
10 |
-
"<|placeholder5|>": 32008,
|
11 |
-
"<|placeholder6|>": 32009,
|
12 |
-
"<|user|>": 32010
|
13 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 32000,
|
3 |
+
"<|assistant|>": 32001,
|
4 |
+
"<|placeholder1|>": 32002,
|
5 |
+
"<|placeholder2|>": 32003,
|
6 |
+
"<|placeholder3|>": 32004,
|
7 |
+
"<|placeholder4|>": 32005,
|
8 |
+
"<|system|>": 32006,
|
9 |
+
"<|end|>": 32007,
|
10 |
+
"<|placeholder5|>": 32008,
|
11 |
+
"<|placeholder6|>": 32009,
|
12 |
+
"<|user|>": 32010
|
13 |
+
}
|
cuda/cuda-fp16/config.json
CHANGED
@@ -1,35 +1,36 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"architectures": [
|
4 |
-
"Phi3ForCausalLM"
|
5 |
-
],
|
6 |
-
"attention_dropout": 0.0,
|
7 |
-
"auto_map": {
|
8 |
-
"AutoConfig": "configuration_phi3.Phi3Config",
|
9 |
-
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
|
10 |
-
},
|
11 |
-
"bos_token_id": 1,
|
12 |
-
"embd_pdrop": 0.0,
|
13 |
-
"eos_token_id": 32000,
|
14 |
-
"hidden_act": "silu",
|
15 |
-
"hidden_size": 3072,
|
16 |
-
"initializer_range": 0.02,
|
17 |
-
"intermediate_size": 8192,
|
18 |
-
"max_position_embeddings": 4096,
|
19 |
-
"model_type": "phi3",
|
20 |
-
"num_attention_heads": 32,
|
21 |
-
"num_hidden_layers": 32,
|
22 |
-
"num_key_value_heads": 32,
|
23 |
-
"original_max_position_embeddings": 4096,
|
24 |
-
"pad_token_id": 32000,
|
25 |
-
"resid_pdrop": 0.0,
|
26 |
-
"rms_norm_eps": 1e-05,
|
27 |
-
"rope_scaling": null,
|
28 |
-
"rope_theta": 10000.0,
|
29 |
-
"sliding_window": 2047,
|
30 |
-
"tie_word_embeddings": false,
|
31 |
-
"torch_dtype": "bfloat16",
|
32 |
-
"transformers_version": "4.
|
33 |
-
"use_cache": true,
|
34 |
-
"
|
35 |
-
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Phi-3-mini-4k-instruct",
|
3 |
+
"architectures": [
|
4 |
+
"Phi3ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"auto_map": {
|
8 |
+
"AutoConfig": "configuration_phi3.Phi3Config",
|
9 |
+
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
|
10 |
+
},
|
11 |
+
"bos_token_id": 1,
|
12 |
+
"embd_pdrop": 0.0,
|
13 |
+
"eos_token_id": 32000,
|
14 |
+
"hidden_act": "silu",
|
15 |
+
"hidden_size": 3072,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 8192,
|
18 |
+
"max_position_embeddings": 4096,
|
19 |
+
"model_type": "phi3",
|
20 |
+
"num_attention_heads": 32,
|
21 |
+
"num_hidden_layers": 32,
|
22 |
+
"num_key_value_heads": 32,
|
23 |
+
"original_max_position_embeddings": 4096,
|
24 |
+
"pad_token_id": 32000,
|
25 |
+
"resid_pdrop": 0.0,
|
26 |
+
"rms_norm_eps": 1e-05,
|
27 |
+
"rope_scaling": null,
|
28 |
+
"rope_theta": 10000.0,
|
29 |
+
"sliding_window": 2047,
|
30 |
+
"tie_word_embeddings": false,
|
31 |
+
"torch_dtype": "bfloat16",
|
32 |
+
"transformers_version": "4.40.2",
|
33 |
+
"use_cache": true,
|
34 |
+
"attention_bias": false,
|
35 |
+
"vocab_size": 32064
|
36 |
+
}
|
cuda/cuda-fp16/configuration_phi3.py
CHANGED
@@ -1,213 +1,227 @@
|
|
1 |
-
# coding=utf-8
|
2 |
-
# Copyright 2024 Microsoft and the HuggingFace Inc. team. All rights reserved.
|
3 |
-
#
|
4 |
-
# Licensed under the Apache License, Version 2.0 (the "License");
|
5 |
-
# you may not use this file except in compliance with the License.
|
6 |
-
# You may obtain a copy of the License at
|
7 |
-
#
|
8 |
-
# http://www.apache.org/licenses/LICENSE-2.0
|
9 |
-
#
|
10 |
-
# Unless required by applicable law or agreed to in writing, software
|
11 |
-
# distributed under the License is distributed on an "AS IS" BASIS,
|
12 |
-
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
13 |
-
# See the License for the specific language governing permissions and
|
14 |
-
# limitations under the License.
|
15 |
-
|
16 |
-
""" Phi-3 model configuration"""
|
17 |
-
|
18 |
-
|
19 |
-
from transformers.configuration_utils import PretrainedConfig
|
20 |
-
from transformers.utils import logging
|
21 |
-
|
22 |
-
|
23 |
-
logger = logging.get_logger(__name__)
|
24 |
-
|
25 |
-
PHI3_PRETRAINED_CONFIG_ARCHIVE_MAP = {
|
26 |
-
"microsoft/Phi-3-mini-4k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/resolve/main/config.json",
|
27 |
-
"microsoft/Phi-3-mini-128k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/config.json",
|
28 |
-
}
|
29 |
-
|
30 |
-
|
31 |
-
class Phi3Config(PretrainedConfig):
|
32 |
-
r"""
|
33 |
-
This is the configuration class to store the configuration of a [`Phi3Model`]. It is used to instantiate a Phi-3
|
34 |
-
model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
|
35 |
-
defaults will yield a similar configuration to that of the
|
36 |
-
[microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct).
|
37 |
-
|
38 |
-
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
|
39 |
-
documentation from [`PretrainedConfig`] for more information.
|
40 |
-
|
41 |
-
Args:
|
42 |
-
vocab_size (`int`, *optional*, defaults to 32064):
|
43 |
-
Vocabulary size of the Phi-3 model. Defines the number of different tokens that can be represented by the
|
44 |
-
`inputs_ids` passed when calling [`Phi3Model`].
|
45 |
-
hidden_size (`int`, *optional*, defaults to 3072):
|
46 |
-
Dimension of the hidden representations.
|
47 |
-
intermediate_size (`int`, *optional*, defaults to 8192):
|
48 |
-
Dimension of the MLP representations.
|
49 |
-
num_hidden_layers (`int`, *optional*, defaults to 32):
|
50 |
-
Number of hidden layers in the Transformer decoder.
|
51 |
-
num_attention_heads (`int`, *optional*, defaults to 32):
|
52 |
-
Number of attention heads for each attention layer in the Transformer decoder.
|
53 |
-
num_key_value_heads (`int`, *optional*):
|
54 |
-
This is the number of key_value heads that should be used to implement Grouped Query Attention. If
|
55 |
-
`num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
|
56 |
-
`num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
|
57 |
-
converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
|
58 |
-
by meanpooling all the original heads within that group. For more details checkout [this
|
59 |
-
paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
|
60 |
-
`num_attention_heads`.
|
61 |
-
resid_pdrop (`float`, *optional*, defaults to 0.0):
|
62 |
-
Dropout probability for mlp outputs.
|
63 |
-
embd_pdrop (`int`, *optional*, defaults to 0.0):
|
64 |
-
The dropout ratio for the embeddings.
|
65 |
-
attention_dropout (`float`, *optional*, defaults to 0.0):
|
66 |
-
The dropout ratio after computing the attention scores.
|
67 |
-
hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
|
68 |
-
The non-linear activation function (function or string) in the decoder.
|
69 |
-
max_position_embeddings (`int`, *optional*, defaults to 4096):
|
70 |
-
The maximum sequence length that this model might ever be used with.
|
71 |
-
original_max_position_embeddings (`int`, *optional*, defaults to 4096):
|
72 |
-
The maximum sequence length that this model was trained with. This is used to determine the size of the
|
73 |
-
original RoPE embeddings when using long scaling.
|
74 |
-
initializer_range (`float`, *optional*, defaults to 0.02):
|
75 |
-
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
|
76 |
-
rms_norm_eps (`float`, *optional*, defaults to 1e-05):
|
77 |
-
The epsilon value used for the RMSNorm.
|
78 |
-
use_cache (`bool`, *optional*, defaults to `True`):
|
79 |
-
Whether or not the model should return the last key/values attentions (not used by all models). Only
|
80 |
-
relevant if `config.is_decoder=True`. Whether to tie weight embeddings or not.
|
81 |
-
tie_word_embeddings (`bool`, *optional*, defaults to `False`):
|
82 |
-
Whether to tie weight embeddings
|
83 |
-
rope_theta (`float`, *optional*, defaults to 10000.0):
|
84 |
-
The base period of the RoPE embeddings.
|
85 |
-
rope_scaling (`dict`, *optional*):
|
86 |
-
The scaling strategy for the RoPE embeddings. If `None`, no scaling is applied. If a dictionary, it must
|
87 |
-
contain the following keys: `type`, `short_factor` and `long_factor`. The `type` must be
|
88 |
-
the `short_factor` and `long_factor` must be lists of numbers with the same length as the hidden size
|
89 |
-
divided by the number of attention heads divided by 2.
|
90 |
-
bos_token_id (`int`, *optional*, defaults to 1):
|
91 |
-
The id of the "beginning-of-sequence" token.
|
92 |
-
eos_token_id (`int`, *optional*, defaults to 32000):
|
93 |
-
The id of the "end-of-sequence" token.
|
94 |
-
pad_token_id (`int`, *optional*, defaults to 32000):
|
95 |
-
The id of the padding token.
|
96 |
-
sliding_window (`int`, *optional*):
|
97 |
-
Sliding window attention window size. If `None`, no sliding window is applied.
|
98 |
-
|
99 |
-
Example:
|
100 |
-
|
101 |
-
```python
|
102 |
-
>>> from transformers import Phi3Model, Phi3Config
|
103 |
-
|
104 |
-
>>> # Initializing a Phi-3 style configuration
|
105 |
-
>>> configuration = Phi3Config.from_pretrained("microsoft/Phi-3-mini-4k-instruct")
|
106 |
-
|
107 |
-
>>> # Initializing a model from the configuration
|
108 |
-
>>> model = Phi3Model(configuration)
|
109 |
-
|
110 |
-
>>> # Accessing the model configuration
|
111 |
-
>>> configuration = model.config
|
112 |
-
```"""
|
113 |
-
|
114 |
-
model_type = "phi3"
|
115 |
-
keys_to_ignore_at_inference = ["past_key_values"]
|
116 |
-
|
117 |
-
def __init__(
|
118 |
-
self,
|
119 |
-
vocab_size=32064,
|
120 |
-
hidden_size=3072,
|
121 |
-
intermediate_size=8192,
|
122 |
-
num_hidden_layers=32,
|
123 |
-
num_attention_heads=32,
|
124 |
-
num_key_value_heads=None,
|
125 |
-
resid_pdrop=0.0,
|
126 |
-
embd_pdrop=0.0,
|
127 |
-
attention_dropout=0.0,
|
128 |
-
hidden_act="silu",
|
129 |
-
max_position_embeddings=4096,
|
130 |
-
original_max_position_embeddings=4096,
|
131 |
-
initializer_range=0.02,
|
132 |
-
rms_norm_eps=1e-5,
|
133 |
-
use_cache=True,
|
134 |
-
tie_word_embeddings=False,
|
135 |
-
rope_theta=10000.0,
|
136 |
-
rope_scaling=None,
|
137 |
-
bos_token_id=1,
|
138 |
-
eos_token_id=32000,
|
139 |
-
pad_token_id=32000,
|
140 |
-
sliding_window=None,
|
141 |
-
**kwargs,
|
142 |
-
):
|
143 |
-
self.vocab_size = vocab_size
|
144 |
-
self.hidden_size = hidden_size
|
145 |
-
self.intermediate_size = intermediate_size
|
146 |
-
self.num_hidden_layers = num_hidden_layers
|
147 |
-
self.num_attention_heads = num_attention_heads
|
148 |
-
|
149 |
-
if num_key_value_heads is None:
|
150 |
-
num_key_value_heads = num_attention_heads
|
151 |
-
|
152 |
-
self.num_key_value_heads = num_key_value_heads
|
153 |
-
self.resid_pdrop = resid_pdrop
|
154 |
-
self.embd_pdrop = embd_pdrop
|
155 |
-
self.attention_dropout = attention_dropout
|
156 |
-
self.hidden_act = hidden_act
|
157 |
-
self.max_position_embeddings = max_position_embeddings
|
158 |
-
self.original_max_position_embeddings = original_max_position_embeddings
|
159 |
-
self.initializer_range = initializer_range
|
160 |
-
self.rms_norm_eps = rms_norm_eps
|
161 |
-
self.use_cache = use_cache
|
162 |
-
self.rope_theta = rope_theta
|
163 |
-
self.rope_scaling = rope_scaling
|
164 |
-
self.
|
165 |
-
self.
|
166 |
-
|
167 |
-
|
168 |
-
|
169 |
-
|
170 |
-
|
171 |
-
|
172 |
-
|
173 |
-
|
174 |
-
|
175 |
-
|
176 |
-
|
177 |
-
|
178 |
-
|
179 |
-
|
180 |
-
|
181 |
-
|
182 |
-
|
183 |
-
|
184 |
-
|
185 |
-
|
186 |
-
|
187 |
-
|
188 |
-
|
189 |
-
|
190 |
-
|
191 |
-
|
192 |
-
|
193 |
-
|
194 |
-
|
195 |
-
|
196 |
-
|
197 |
-
|
198 |
-
|
199 |
-
|
200 |
-
|
201 |
-
|
202 |
-
|
203 |
-
|
204 |
-
|
205 |
-
|
206 |
-
|
207 |
-
|
208 |
-
|
209 |
-
|
210 |
-
|
211 |
-
|
212 |
-
|
213 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# coding=utf-8
|
2 |
+
# Copyright 2024 Microsoft and the HuggingFace Inc. team. All rights reserved.
|
3 |
+
#
|
4 |
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
5 |
+
# you may not use this file except in compliance with the License.
|
6 |
+
# You may obtain a copy of the License at
|
7 |
+
#
|
8 |
+
# http://www.apache.org/licenses/LICENSE-2.0
|
9 |
+
#
|
10 |
+
# Unless required by applicable law or agreed to in writing, software
|
11 |
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
12 |
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
13 |
+
# See the License for the specific language governing permissions and
|
14 |
+
# limitations under the License.
|
15 |
+
|
16 |
+
""" Phi-3 model configuration"""
|
17 |
+
|
18 |
+
|
19 |
+
from transformers.configuration_utils import PretrainedConfig
|
20 |
+
from transformers.utils import logging
|
21 |
+
|
22 |
+
|
23 |
+
logger = logging.get_logger(__name__)
|
24 |
+
|
25 |
+
PHI3_PRETRAINED_CONFIG_ARCHIVE_MAP = {
|
26 |
+
"microsoft/Phi-3-mini-4k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/resolve/main/config.json",
|
27 |
+
"microsoft/Phi-3-mini-128k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/config.json",
|
28 |
+
}
|
29 |
+
|
30 |
+
|
31 |
+
class Phi3Config(PretrainedConfig):
|
32 |
+
r"""
|
33 |
+
This is the configuration class to store the configuration of a [`Phi3Model`]. It is used to instantiate a Phi-3
|
34 |
+
model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
|
35 |
+
defaults will yield a similar configuration to that of the
|
36 |
+
[microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct).
|
37 |
+
|
38 |
+
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
|
39 |
+
documentation from [`PretrainedConfig`] for more information.
|
40 |
+
|
41 |
+
Args:
|
42 |
+
vocab_size (`int`, *optional*, defaults to 32064):
|
43 |
+
Vocabulary size of the Phi-3 model. Defines the number of different tokens that can be represented by the
|
44 |
+
`inputs_ids` passed when calling [`Phi3Model`].
|
45 |
+
hidden_size (`int`, *optional*, defaults to 3072):
|
46 |
+
Dimension of the hidden representations.
|
47 |
+
intermediate_size (`int`, *optional*, defaults to 8192):
|
48 |
+
Dimension of the MLP representations.
|
49 |
+
num_hidden_layers (`int`, *optional*, defaults to 32):
|
50 |
+
Number of hidden layers in the Transformer decoder.
|
51 |
+
num_attention_heads (`int`, *optional*, defaults to 32):
|
52 |
+
Number of attention heads for each attention layer in the Transformer decoder.
|
53 |
+
num_key_value_heads (`int`, *optional*):
|
54 |
+
This is the number of key_value heads that should be used to implement Grouped Query Attention. If
|
55 |
+
`num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
|
56 |
+
`num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
|
57 |
+
converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
|
58 |
+
by meanpooling all the original heads within that group. For more details checkout [this
|
59 |
+
paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
|
60 |
+
`num_attention_heads`.
|
61 |
+
resid_pdrop (`float`, *optional*, defaults to 0.0):
|
62 |
+
Dropout probability for mlp outputs.
|
63 |
+
embd_pdrop (`int`, *optional*, defaults to 0.0):
|
64 |
+
The dropout ratio for the embeddings.
|
65 |
+
attention_dropout (`float`, *optional*, defaults to 0.0):
|
66 |
+
The dropout ratio after computing the attention scores.
|
67 |
+
hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
|
68 |
+
The non-linear activation function (function or string) in the decoder.
|
69 |
+
max_position_embeddings (`int`, *optional*, defaults to 4096):
|
70 |
+
The maximum sequence length that this model might ever be used with.
|
71 |
+
original_max_position_embeddings (`int`, *optional*, defaults to 4096):
|
72 |
+
The maximum sequence length that this model was trained with. This is used to determine the size of the
|
73 |
+
original RoPE embeddings when using long scaling.
|
74 |
+
initializer_range (`float`, *optional*, defaults to 0.02):
|
75 |
+
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
|
76 |
+
rms_norm_eps (`float`, *optional*, defaults to 1e-05):
|
77 |
+
The epsilon value used for the RMSNorm.
|
78 |
+
use_cache (`bool`, *optional*, defaults to `True`):
|
79 |
+
Whether or not the model should return the last key/values attentions (not used by all models). Only
|
80 |
+
relevant if `config.is_decoder=True`. Whether to tie weight embeddings or not.
|
81 |
+
tie_word_embeddings (`bool`, *optional*, defaults to `False`):
|
82 |
+
Whether to tie weight embeddings
|
83 |
+
rope_theta (`float`, *optional*, defaults to 10000.0):
|
84 |
+
The base period of the RoPE embeddings.
|
85 |
+
rope_scaling (`dict`, *optional*):
|
86 |
+
The scaling strategy for the RoPE embeddings. If `None`, no scaling is applied. If a dictionary, it must
|
87 |
+
contain the following keys: `type`, `short_factor` and `long_factor`. The `type` must be `longrope` and
|
88 |
+
the `short_factor` and `long_factor` must be lists of numbers with the same length as the hidden size
|
89 |
+
divided by the number of attention heads divided by 2.
|
90 |
+
bos_token_id (`int`, *optional*, defaults to 1):
|
91 |
+
The id of the "beginning-of-sequence" token.
|
92 |
+
eos_token_id (`int`, *optional*, defaults to 32000):
|
93 |
+
The id of the "end-of-sequence" token.
|
94 |
+
pad_token_id (`int`, *optional*, defaults to 32000):
|
95 |
+
The id of the padding token.
|
96 |
+
sliding_window (`int`, *optional*):
|
97 |
+
Sliding window attention window size. If `None`, no sliding window is applied.
|
98 |
+
|
99 |
+
Example:
|
100 |
+
|
101 |
+
```python
|
102 |
+
>>> from transformers import Phi3Model, Phi3Config
|
103 |
+
|
104 |
+
>>> # Initializing a Phi-3 style configuration
|
105 |
+
>>> configuration = Phi3Config.from_pretrained("microsoft/Phi-3-mini-4k-instruct")
|
106 |
+
|
107 |
+
>>> # Initializing a model from the configuration
|
108 |
+
>>> model = Phi3Model(configuration)
|
109 |
+
|
110 |
+
>>> # Accessing the model configuration
|
111 |
+
>>> configuration = model.config
|
112 |
+
```"""
|
113 |
+
|
114 |
+
model_type = "phi3"
|
115 |
+
keys_to_ignore_at_inference = ["past_key_values"]
|
116 |
+
|
117 |
+
def __init__(
|
118 |
+
self,
|
119 |
+
vocab_size=32064,
|
120 |
+
hidden_size=3072,
|
121 |
+
intermediate_size=8192,
|
122 |
+
num_hidden_layers=32,
|
123 |
+
num_attention_heads=32,
|
124 |
+
num_key_value_heads=None,
|
125 |
+
resid_pdrop=0.0,
|
126 |
+
embd_pdrop=0.0,
|
127 |
+
attention_dropout=0.0,
|
128 |
+
hidden_act="silu",
|
129 |
+
max_position_embeddings=4096,
|
130 |
+
original_max_position_embeddings=4096,
|
131 |
+
initializer_range=0.02,
|
132 |
+
rms_norm_eps=1e-5,
|
133 |
+
use_cache=True,
|
134 |
+
tie_word_embeddings=False,
|
135 |
+
rope_theta=10000.0,
|
136 |
+
rope_scaling=None,
|
137 |
+
bos_token_id=1,
|
138 |
+
eos_token_id=32000,
|
139 |
+
pad_token_id=32000,
|
140 |
+
sliding_window=None,
|
141 |
+
**kwargs,
|
142 |
+
):
|
143 |
+
self.vocab_size = vocab_size
|
144 |
+
self.hidden_size = hidden_size
|
145 |
+
self.intermediate_size = intermediate_size
|
146 |
+
self.num_hidden_layers = num_hidden_layers
|
147 |
+
self.num_attention_heads = num_attention_heads
|
148 |
+
|
149 |
+
if num_key_value_heads is None:
|
150 |
+
num_key_value_heads = num_attention_heads
|
151 |
+
|
152 |
+
self.num_key_value_heads = num_key_value_heads
|
153 |
+
self.resid_pdrop = resid_pdrop
|
154 |
+
self.embd_pdrop = embd_pdrop
|
155 |
+
self.attention_dropout = attention_dropout
|
156 |
+
self.hidden_act = hidden_act
|
157 |
+
self.max_position_embeddings = max_position_embeddings
|
158 |
+
self.original_max_position_embeddings = original_max_position_embeddings
|
159 |
+
self.initializer_range = initializer_range
|
160 |
+
self.rms_norm_eps = rms_norm_eps
|
161 |
+
self.use_cache = use_cache
|
162 |
+
self.rope_theta = rope_theta
|
163 |
+
self.rope_scaling = rope_scaling
|
164 |
+
self._rope_scaling_adjustment()
|
165 |
+
self._rope_scaling_validation()
|
166 |
+
self.sliding_window = sliding_window
|
167 |
+
|
168 |
+
super().__init__(
|
169 |
+
bos_token_id=bos_token_id,
|
170 |
+
eos_token_id=eos_token_id,
|
171 |
+
pad_token_id=pad_token_id,
|
172 |
+
tie_word_embeddings=tie_word_embeddings,
|
173 |
+
**kwargs,
|
174 |
+
)
|
175 |
+
|
176 |
+
def _rope_scaling_adjustment(self):
|
177 |
+
"""
|
178 |
+
Adjust the `type` of the `rope_scaling` configuration for backward compatibility.
|
179 |
+
"""
|
180 |
+
if self.rope_scaling is None:
|
181 |
+
return
|
182 |
+
|
183 |
+
rope_scaling_type = self.rope_scaling.get("type", None)
|
184 |
+
|
185 |
+
# For backward compatibility if previous version used "su" or "yarn"
|
186 |
+
if rope_scaling_type is not None and rope_scaling_type in ["su", "yarn"]:
|
187 |
+
self.rope_scaling["type"] = "longrope"
|
188 |
+
|
189 |
+
def _rope_scaling_validation(self):
|
190 |
+
"""
|
191 |
+
Validate the `rope_scaling` configuration.
|
192 |
+
"""
|
193 |
+
if self.rope_scaling is None:
|
194 |
+
return
|
195 |
+
|
196 |
+
if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 3:
|
197 |
+
raise ValueError(
|
198 |
+
"`rope_scaling` must be a dictionary with three fields, `type`, `short_factor` and `long_factor`, "
|
199 |
+
f"got {self.rope_scaling}"
|
200 |
+
)
|
201 |
+
rope_scaling_type = self.rope_scaling.get("type", None)
|
202 |
+
rope_scaling_short_factor = self.rope_scaling.get("short_factor", None)
|
203 |
+
rope_scaling_long_factor = self.rope_scaling.get("long_factor", None)
|
204 |
+
if rope_scaling_type is None or rope_scaling_type not in ["longrope"]:
|
205 |
+
raise ValueError(f"`rope_scaling`'s type field must be one of ['longrope'], got {rope_scaling_type}")
|
206 |
+
if not (
|
207 |
+
isinstance(rope_scaling_short_factor, list)
|
208 |
+
and all(isinstance(x, (int, float)) for x in rope_scaling_short_factor)
|
209 |
+
):
|
210 |
+
raise ValueError(
|
211 |
+
f"`rope_scaling`'s short_factor field must be a list of numbers, got {rope_scaling_short_factor}"
|
212 |
+
)
|
213 |
+
if not len(rope_scaling_short_factor) == self.hidden_size // self.num_attention_heads // 2:
|
214 |
+
raise ValueError(
|
215 |
+
f"`rope_scaling`'s short_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_short_factor)}"
|
216 |
+
)
|
217 |
+
if not (
|
218 |
+
isinstance(rope_scaling_long_factor, list)
|
219 |
+
and all(isinstance(x, (int, float)) for x in rope_scaling_long_factor)
|
220 |
+
):
|
221 |
+
raise ValueError(
|
222 |
+
f"`rope_scaling`'s long_factor field must be a list of numbers, got {rope_scaling_long_factor}"
|
223 |
+
)
|
224 |
+
if not len(rope_scaling_long_factor) == self.hidden_size // self.num_attention_heads // 2:
|
225 |
+
raise ValueError(
|
226 |
+
f"`rope_scaling`'s long_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_long_factor)}"
|
227 |
+
)
|
cuda/cuda-fp16/genai_config.json
CHANGED
@@ -56,4 +56,4 @@
|
|
56 |
"top_k": 1,
|
57 |
"top_p": 1.0
|
58 |
}
|
59 |
-
}
|
|
|
56 |
"top_k": 1,
|
57 |
"top_p": 1.0
|
58 |
}
|
59 |
+
}
|
cuda/cuda-fp16/phi3-mini-4k-instruct-cuda-fp16.onnx.data
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7642945536
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f340f6b302ee11e813c253f5e861dcfc2afe99bfd35c808fef5391fbc08961d
|
3 |
size 7642945536
|
cuda/cuda-fp16/special_tokens_map.json
CHANGED
@@ -1,30 +1,30 @@
|
|
1 |
-
{
|
2 |
-
"bos_token": {
|
3 |
-
"content": "<s>",
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": false,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"eos_token": {
|
10 |
-
"content": "<|endoftext|>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"pad_token": {
|
17 |
-
"content": "<|endoftext|>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"unk_token": {
|
24 |
-
"content": "<unk>",
|
25 |
-
"lstrip": false,
|
26 |
-
"normalized": false,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
}
|
30 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
cuda/cuda-fp16/tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
cuda/cuda-fp16/tokenizer_config.json
CHANGED
@@ -1,130 +1,130 @@
|
|
1 |
-
{
|
2 |
-
"add_bos_token":
|
3 |
-
"add_eos_token": false,
|
4 |
-
"added_tokens_decoder": {
|
5 |
-
"0": {
|
6 |
-
"content": "<unk>",
|
7 |
-
"lstrip": false,
|
8 |
-
"normalized": false,
|
9 |
-
"rstrip": false,
|
10 |
-
"single_word": false,
|
11 |
-
"special": true
|
12 |
-
},
|
13 |
-
"1": {
|
14 |
-
"content": "<s>",
|
15 |
-
"lstrip": false,
|
16 |
-
"normalized": false,
|
17 |
-
"rstrip": false,
|
18 |
-
"single_word": false,
|
19 |
-
"special": true
|
20 |
-
},
|
21 |
-
"2": {
|
22 |
-
"content": "</s>",
|
23 |
-
"lstrip": false,
|
24 |
-
"normalized": false,
|
25 |
-
"rstrip": true,
|
26 |
-
"single_word": false,
|
27 |
-
"special": false
|
28 |
-
},
|
29 |
-
"32000": {
|
30 |
-
"content": "<|endoftext|>",
|
31 |
-
"lstrip": false,
|
32 |
-
"normalized": false,
|
33 |
-
"rstrip": false,
|
34 |
-
"single_word": false,
|
35 |
-
"special": true
|
36 |
-
},
|
37 |
-
"32001": {
|
38 |
-
"content": "<|assistant|>",
|
39 |
-
"lstrip": false,
|
40 |
-
"normalized": false,
|
41 |
-
"rstrip": true,
|
42 |
-
"single_word": false,
|
43 |
-
"special": true
|
44 |
-
},
|
45 |
-
"32002": {
|
46 |
-
"content": "<|placeholder1|>",
|
47 |
-
"lstrip": false,
|
48 |
-
"normalized": false,
|
49 |
-
"rstrip": true,
|
50 |
-
"single_word": false,
|
51 |
-
"special": true
|
52 |
-
},
|
53 |
-
"32003": {
|
54 |
-
"content": "<|placeholder2|>",
|
55 |
-
"lstrip": false,
|
56 |
-
"normalized": false,
|
57 |
-
"rstrip": true,
|
58 |
-
"single_word": false,
|
59 |
-
"special": true
|
60 |
-
},
|
61 |
-
"32004": {
|
62 |
-
"content": "<|placeholder3|>",
|
63 |
-
"lstrip": false,
|
64 |
-
"normalized": false,
|
65 |
-
"rstrip": true,
|
66 |
-
"single_word": false,
|
67 |
-
"special": true
|
68 |
-
},
|
69 |
-
"32005": {
|
70 |
-
"content": "<|placeholder4|>",
|
71 |
-
"lstrip": false,
|
72 |
-
"normalized": false,
|
73 |
-
"rstrip": true,
|
74 |
-
"single_word": false,
|
75 |
-
"special": true
|
76 |
-
},
|
77 |
-
"32006": {
|
78 |
-
"content": "<|system|>",
|
79 |
-
"lstrip": false,
|
80 |
-
"normalized": false,
|
81 |
-
"rstrip": true,
|
82 |
-
"single_word": false,
|
83 |
-
"special": true
|
84 |
-
},
|
85 |
-
"32007": {
|
86 |
-
"content": "<|end|>",
|
87 |
-
"lstrip": false,
|
88 |
-
"normalized": false,
|
89 |
-
"rstrip": true,
|
90 |
-
"single_word": false,
|
91 |
-
"special": true
|
92 |
-
},
|
93 |
-
"32008": {
|
94 |
-
"content": "<|placeholder5|>",
|
95 |
-
"lstrip": false,
|
96 |
-
"normalized": false,
|
97 |
-
"rstrip": true,
|
98 |
-
"single_word": false,
|
99 |
-
"special": true
|
100 |
-
},
|
101 |
-
"32009": {
|
102 |
-
"content": "<|placeholder6|>",
|
103 |
-
"lstrip": false,
|
104 |
-
"normalized": false,
|
105 |
-
"rstrip": true,
|
106 |
-
"single_word": false,
|
107 |
-
"special": true
|
108 |
-
},
|
109 |
-
"32010": {
|
110 |
-
"content": "<|user|>",
|
111 |
-
"lstrip": false,
|
112 |
-
"normalized": false,
|
113 |
-
"rstrip": true,
|
114 |
-
"single_word": false,
|
115 |
-
"special": true
|
116 |
-
}
|
117 |
-
},
|
118 |
-
"bos_token": "<s>",
|
119 |
-
"chat_template": "{
|
120 |
-
"clean_up_tokenization_spaces": false,
|
121 |
-
"eos_token": "<|endoftext|>",
|
122 |
-
"legacy": false,
|
123 |
-
"model_max_length": 4096,
|
124 |
-
"pad_token": "<|endoftext|>",
|
125 |
-
"padding_side": "left",
|
126 |
-
"sp_model_kwargs": {},
|
127 |
-
"tokenizer_class": "LlamaTokenizer",
|
128 |
-
"unk_token": "<unk>",
|
129 |
-
"use_default_system_prompt": false
|
130 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": true,
|
26 |
+
"single_word": false,
|
27 |
+
"special": false
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "<|endoftext|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"32001": {
|
38 |
+
"content": "<|assistant|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": true,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"32002": {
|
46 |
+
"content": "<|placeholder1|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": true,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"32003": {
|
54 |
+
"content": "<|placeholder2|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": true,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"32004": {
|
62 |
+
"content": "<|placeholder3|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": true,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"32005": {
|
70 |
+
"content": "<|placeholder4|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": true,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"32006": {
|
78 |
+
"content": "<|system|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": true,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"32007": {
|
86 |
+
"content": "<|end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": true,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"32008": {
|
94 |
+
"content": "<|placeholder5|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": true,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"32009": {
|
102 |
+
"content": "<|placeholder6|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": true,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"32010": {
|
110 |
+
"content": "<|user|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": true,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
}
|
117 |
+
},
|
118 |
+
"bos_token": "<s>",
|
119 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
|
120 |
+
"clean_up_tokenization_spaces": false,
|
121 |
+
"eos_token": "<|endoftext|>",
|
122 |
+
"legacy": false,
|
123 |
+
"model_max_length": 4096,
|
124 |
+
"pad_token": "<|endoftext|>",
|
125 |
+
"padding_side": "left",
|
126 |
+
"sp_model_kwargs": {},
|
127 |
+
"tokenizer_class": "LlamaTokenizer",
|
128 |
+
"unk_token": "<unk>",
|
129 |
+
"use_default_system_prompt": false
|
130 |
+
}
|
cuda/cuda-int4-awq-block-128/added_tokens.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 32000,
|
3 |
+
"<|assistant|>": 32001,
|
4 |
+
"<|placeholder1|>": 32002,
|
5 |
+
"<|placeholder2|>": 32003,
|
6 |
+
"<|placeholder3|>": 32004,
|
7 |
+
"<|placeholder4|>": 32005,
|
8 |
+
"<|system|>": 32006,
|
9 |
+
"<|end|>": 32007,
|
10 |
+
"<|placeholder5|>": 32008,
|
11 |
+
"<|placeholder6|>": 32009,
|
12 |
+
"<|user|>": 32010
|
13 |
+
}
|
cuda/cuda-int4-awq-block-128/config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Phi-3-mini-4k-instruct",
|
3 |
+
"architectures": [
|
4 |
+
"Phi3ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"auto_map": {
|
8 |
+
"AutoConfig": "configuration_phi3.Phi3Config",
|
9 |
+
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
|
10 |
+
},
|
11 |
+
"bos_token_id": 1,
|
12 |
+
"embd_pdrop": 0.0,
|
13 |
+
"eos_token_id": 32000,
|
14 |
+
"hidden_act": "silu",
|
15 |
+
"hidden_size": 3072,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 8192,
|
18 |
+
"max_position_embeddings": 4096,
|
19 |
+
"model_type": "phi3",
|
20 |
+
"num_attention_heads": 32,
|
21 |
+
"num_hidden_layers": 32,
|
22 |
+
"num_key_value_heads": 32,
|
23 |
+
"original_max_position_embeddings": 4096,
|
24 |
+
"pad_token_id": 32000,
|
25 |
+
"resid_pdrop": 0.0,
|
26 |
+
"rms_norm_eps": 1e-05,
|
27 |
+
"rope_scaling": null,
|
28 |
+
"rope_theta": 10000.0,
|
29 |
+
"sliding_window": 2047,
|
30 |
+
"tie_word_embeddings": false,
|
31 |
+
"torch_dtype": "bfloat16",
|
32 |
+
"transformers_version": "4.40.2",
|
33 |
+
"use_cache": true,
|
34 |
+
"attention_bias": false,
|
35 |
+
"vocab_size": 32064
|
36 |
+
}
|
cuda/cuda-int4-awq-block-128/configuration_phi3.py
ADDED
@@ -0,0 +1,227 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# coding=utf-8
|
2 |
+
# Copyright 2024 Microsoft and the HuggingFace Inc. team. All rights reserved.
|
3 |
+
#
|
4 |
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
5 |
+
# you may not use this file except in compliance with the License.
|
6 |
+
# You may obtain a copy of the License at
|
7 |
+
#
|
8 |
+
# http://www.apache.org/licenses/LICENSE-2.0
|
9 |
+
#
|
10 |
+
# Unless required by applicable law or agreed to in writing, software
|
11 |
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
12 |
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
13 |
+
# See the License for the specific language governing permissions and
|
14 |
+
# limitations under the License.
|
15 |
+
|
16 |
+
""" Phi-3 model configuration"""
|
17 |
+
|
18 |
+
|
19 |
+
from transformers.configuration_utils import PretrainedConfig
|
20 |
+
from transformers.utils import logging
|
21 |
+
|
22 |
+
|
23 |
+
logger = logging.get_logger(__name__)
|
24 |
+
|
25 |
+
PHI3_PRETRAINED_CONFIG_ARCHIVE_MAP = {
|
26 |
+
"microsoft/Phi-3-mini-4k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/resolve/main/config.json",
|
27 |
+
"microsoft/Phi-3-mini-128k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/config.json",
|
28 |
+
}
|
29 |
+
|
30 |
+
|
31 |
+
class Phi3Config(PretrainedConfig):
|
32 |
+
r"""
|
33 |
+
This is the configuration class to store the configuration of a [`Phi3Model`]. It is used to instantiate a Phi-3
|
34 |
+
model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
|
35 |
+
defaults will yield a similar configuration to that of the
|
36 |
+
[microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct).
|
37 |
+
|
38 |
+
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
|
39 |
+
documentation from [`PretrainedConfig`] for more information.
|
40 |
+
|
41 |
+
Args:
|
42 |
+
vocab_size (`int`, *optional*, defaults to 32064):
|
43 |
+
Vocabulary size of the Phi-3 model. Defines the number of different tokens that can be represented by the
|
44 |
+
`inputs_ids` passed when calling [`Phi3Model`].
|
45 |
+
hidden_size (`int`, *optional*, defaults to 3072):
|
46 |
+
Dimension of the hidden representations.
|
47 |
+
intermediate_size (`int`, *optional*, defaults to 8192):
|
48 |
+
Dimension of the MLP representations.
|
49 |
+
num_hidden_layers (`int`, *optional*, defaults to 32):
|
50 |
+
Number of hidden layers in the Transformer decoder.
|
51 |
+
num_attention_heads (`int`, *optional*, defaults to 32):
|
52 |
+
Number of attention heads for each attention layer in the Transformer decoder.
|
53 |
+
num_key_value_heads (`int`, *optional*):
|
54 |
+
This is the number of key_value heads that should be used to implement Grouped Query Attention. If
|
55 |
+
`num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
|
56 |
+
`num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
|
57 |
+
converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
|
58 |
+
by meanpooling all the original heads within that group. For more details checkout [this
|
59 |
+
paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
|
60 |
+
`num_attention_heads`.
|
61 |
+
resid_pdrop (`float`, *optional*, defaults to 0.0):
|
62 |
+
Dropout probability for mlp outputs.
|
63 |
+
embd_pdrop (`int`, *optional*, defaults to 0.0):
|
64 |
+
The dropout ratio for the embeddings.
|
65 |
+
attention_dropout (`float`, *optional*, defaults to 0.0):
|
66 |
+
The dropout ratio after computing the attention scores.
|
67 |
+
hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
|
68 |
+
The non-linear activation function (function or string) in the decoder.
|
69 |
+
max_position_embeddings (`int`, *optional*, defaults to 4096):
|
70 |
+
The maximum sequence length that this model might ever be used with.
|
71 |
+
original_max_position_embeddings (`int`, *optional*, defaults to 4096):
|
72 |
+
The maximum sequence length that this model was trained with. This is used to determine the size of the
|
73 |
+
original RoPE embeddings when using long scaling.
|
74 |
+
initializer_range (`float`, *optional*, defaults to 0.02):
|
75 |
+
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
|
76 |
+
rms_norm_eps (`float`, *optional*, defaults to 1e-05):
|
77 |
+
The epsilon value used for the RMSNorm.
|
78 |
+
use_cache (`bool`, *optional*, defaults to `True`):
|
79 |
+
Whether or not the model should return the last key/values attentions (not used by all models). Only
|
80 |
+
relevant if `config.is_decoder=True`. Whether to tie weight embeddings or not.
|
81 |
+
tie_word_embeddings (`bool`, *optional*, defaults to `False`):
|
82 |
+
Whether to tie weight embeddings
|
83 |
+
rope_theta (`float`, *optional*, defaults to 10000.0):
|
84 |
+
The base period of the RoPE embeddings.
|
85 |
+
rope_scaling (`dict`, *optional*):
|
86 |
+
The scaling strategy for the RoPE embeddings. If `None`, no scaling is applied. If a dictionary, it must
|
87 |
+
contain the following keys: `type`, `short_factor` and `long_factor`. The `type` must be `longrope` and
|
88 |
+
the `short_factor` and `long_factor` must be lists of numbers with the same length as the hidden size
|
89 |
+
divided by the number of attention heads divided by 2.
|
90 |
+
bos_token_id (`int`, *optional*, defaults to 1):
|
91 |
+
The id of the "beginning-of-sequence" token.
|
92 |
+
eos_token_id (`int`, *optional*, defaults to 32000):
|
93 |
+
The id of the "end-of-sequence" token.
|
94 |
+
pad_token_id (`int`, *optional*, defaults to 32000):
|
95 |
+
The id of the padding token.
|
96 |
+
sliding_window (`int`, *optional*):
|
97 |
+
Sliding window attention window size. If `None`, no sliding window is applied.
|
98 |
+
|
99 |
+
Example:
|
100 |
+
|
101 |
+
```python
|
102 |
+
>>> from transformers import Phi3Model, Phi3Config
|
103 |
+
|
104 |
+
>>> # Initializing a Phi-3 style configuration
|
105 |
+
>>> configuration = Phi3Config.from_pretrained("microsoft/Phi-3-mini-4k-instruct")
|
106 |
+
|
107 |
+
>>> # Initializing a model from the configuration
|
108 |
+
>>> model = Phi3Model(configuration)
|
109 |
+
|
110 |
+
>>> # Accessing the model configuration
|
111 |
+
>>> configuration = model.config
|
112 |
+
```"""
|
113 |
+
|
114 |
+
model_type = "phi3"
|
115 |
+
keys_to_ignore_at_inference = ["past_key_values"]
|
116 |
+
|
117 |
+
def __init__(
|
118 |
+
self,
|
119 |
+
vocab_size=32064,
|
120 |
+
hidden_size=3072,
|
121 |
+
intermediate_size=8192,
|
122 |
+
num_hidden_layers=32,
|
123 |
+
num_attention_heads=32,
|
124 |
+
num_key_value_heads=None,
|
125 |
+
resid_pdrop=0.0,
|
126 |
+
embd_pdrop=0.0,
|
127 |
+
attention_dropout=0.0,
|
128 |
+
hidden_act="silu",
|
129 |
+
max_position_embeddings=4096,
|
130 |
+
original_max_position_embeddings=4096,
|
131 |
+
initializer_range=0.02,
|
132 |
+
rms_norm_eps=1e-5,
|
133 |
+
use_cache=True,
|
134 |
+
tie_word_embeddings=False,
|
135 |
+
rope_theta=10000.0,
|
136 |
+
rope_scaling=None,
|
137 |
+
bos_token_id=1,
|
138 |
+
eos_token_id=32000,
|
139 |
+
pad_token_id=32000,
|
140 |
+
sliding_window=None,
|
141 |
+
**kwargs,
|
142 |
+
):
|
143 |
+
self.vocab_size = vocab_size
|
144 |
+
self.hidden_size = hidden_size
|
145 |
+
self.intermediate_size = intermediate_size
|
146 |
+
self.num_hidden_layers = num_hidden_layers
|
147 |
+
self.num_attention_heads = num_attention_heads
|
148 |
+
|
149 |
+
if num_key_value_heads is None:
|
150 |
+
num_key_value_heads = num_attention_heads
|
151 |
+
|
152 |
+
self.num_key_value_heads = num_key_value_heads
|
153 |
+
self.resid_pdrop = resid_pdrop
|
154 |
+
self.embd_pdrop = embd_pdrop
|
155 |
+
self.attention_dropout = attention_dropout
|
156 |
+
self.hidden_act = hidden_act
|
157 |
+
self.max_position_embeddings = max_position_embeddings
|
158 |
+
self.original_max_position_embeddings = original_max_position_embeddings
|
159 |
+
self.initializer_range = initializer_range
|
160 |
+
self.rms_norm_eps = rms_norm_eps
|
161 |
+
self.use_cache = use_cache
|
162 |
+
self.rope_theta = rope_theta
|
163 |
+
self.rope_scaling = rope_scaling
|
164 |
+
self._rope_scaling_adjustment()
|
165 |
+
self._rope_scaling_validation()
|
166 |
+
self.sliding_window = sliding_window
|
167 |
+
|
168 |
+
super().__init__(
|
169 |
+
bos_token_id=bos_token_id,
|
170 |
+
eos_token_id=eos_token_id,
|
171 |
+
pad_token_id=pad_token_id,
|
172 |
+
tie_word_embeddings=tie_word_embeddings,
|
173 |
+
**kwargs,
|
174 |
+
)
|
175 |
+
|
176 |
+
def _rope_scaling_adjustment(self):
|
177 |
+
"""
|
178 |
+
Adjust the `type` of the `rope_scaling` configuration for backward compatibility.
|
179 |
+
"""
|
180 |
+
if self.rope_scaling is None:
|
181 |
+
return
|
182 |
+
|
183 |
+
rope_scaling_type = self.rope_scaling.get("type", None)
|
184 |
+
|
185 |
+
# For backward compatibility if previous version used "su" or "yarn"
|
186 |
+
if rope_scaling_type is not None and rope_scaling_type in ["su", "yarn"]:
|
187 |
+
self.rope_scaling["type"] = "longrope"
|
188 |
+
|
189 |
+
def _rope_scaling_validation(self):
|
190 |
+
"""
|
191 |
+
Validate the `rope_scaling` configuration.
|
192 |
+
"""
|
193 |
+
if self.rope_scaling is None:
|
194 |
+
return
|
195 |
+
|
196 |
+
if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 3:
|
197 |
+
raise ValueError(
|
198 |
+
"`rope_scaling` must be a dictionary with three fields, `type`, `short_factor` and `long_factor`, "
|
199 |
+
f"got {self.rope_scaling}"
|
200 |
+
)
|
201 |
+
rope_scaling_type = self.rope_scaling.get("type", None)
|
202 |
+
rope_scaling_short_factor = self.rope_scaling.get("short_factor", None)
|
203 |
+
rope_scaling_long_factor = self.rope_scaling.get("long_factor", None)
|
204 |
+
if rope_scaling_type is None or rope_scaling_type not in ["longrope"]:
|
205 |
+
raise ValueError(f"`rope_scaling`'s type field must be one of ['longrope'], got {rope_scaling_type}")
|
206 |
+
if not (
|
207 |
+
isinstance(rope_scaling_short_factor, list)
|
208 |
+
and all(isinstance(x, (int, float)) for x in rope_scaling_short_factor)
|
209 |
+
):
|
210 |
+
raise ValueError(
|
211 |
+
f"`rope_scaling`'s short_factor field must be a list of numbers, got {rope_scaling_short_factor}"
|
212 |
+
)
|
213 |
+
if not len(rope_scaling_short_factor) == self.hidden_size // self.num_attention_heads // 2:
|
214 |
+
raise ValueError(
|
215 |
+
f"`rope_scaling`'s short_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_short_factor)}"
|
216 |
+
)
|
217 |
+
if not (
|
218 |
+
isinstance(rope_scaling_long_factor, list)
|
219 |
+
and all(isinstance(x, (int, float)) for x in rope_scaling_long_factor)
|
220 |
+
):
|
221 |
+
raise ValueError(
|
222 |
+
f"`rope_scaling`'s long_factor field must be a list of numbers, got {rope_scaling_long_factor}"
|
223 |
+
)
|
224 |
+
if not len(rope_scaling_long_factor) == self.hidden_size // self.num_attention_heads // 2:
|
225 |
+
raise ValueError(
|
226 |
+
f"`rope_scaling`'s long_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_long_factor)}"
|
227 |
+
)
|
cuda/cuda-int4-awq-block-128/genai_config.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model": {
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"context_length": 4096,
|
5 |
+
"decoder": {
|
6 |
+
"session_options": {
|
7 |
+
"log_id": "onnxruntime-genai",
|
8 |
+
"provider_options": [
|
9 |
+
{
|
10 |
+
"cuda": {
|
11 |
+
"enable_cuda_graph": "0"
|
12 |
+
}
|
13 |
+
}
|
14 |
+
]
|
15 |
+
},
|
16 |
+
"filename": "phi3-mini-4k-instruct-cuda-int4-awq-block-128.onnx",
|
17 |
+
"head_size": 96,
|
18 |
+
"hidden_size": 3072,
|
19 |
+
"inputs": {
|
20 |
+
"input_ids": "input_ids",
|
21 |
+
"attention_mask": "attention_mask",
|
22 |
+
"past_key_names": "past_key_values.%d.key",
|
23 |
+
"past_value_names": "past_key_values.%d.value"
|
24 |
+
},
|
25 |
+
"outputs": {
|
26 |
+
"logits": "logits",
|
27 |
+
"present_key_names": "present.%d.key",
|
28 |
+
"present_value_names": "present.%d.value"
|
29 |
+
},
|
30 |
+
"num_attention_heads": 32,
|
31 |
+
"num_hidden_layers": 32,
|
32 |
+
"num_key_value_heads": 32
|
33 |
+
},
|
34 |
+
"eos_token_id": [
|
35 |
+
32000,
|
36 |
+
32001,
|
37 |
+
32007
|
38 |
+
],
|
39 |
+
"pad_token_id": 32000,
|
40 |
+
"type": "phi3",
|
41 |
+
"vocab_size": 32064
|
42 |
+
},
|
43 |
+
"search": {
|
44 |
+
"diversity_penalty": 0.0,
|
45 |
+
"do_sample": false,
|
46 |
+
"early_stopping": true,
|
47 |
+
"length_penalty": 1.0,
|
48 |
+
"max_length": 4096,
|
49 |
+
"min_length": 0,
|
50 |
+
"no_repeat_ngram_size": 0,
|
51 |
+
"num_beams": 1,
|
52 |
+
"num_return_sequences": 1,
|
53 |
+
"past_present_share_buffer": true,
|
54 |
+
"repetition_penalty": 1.0,
|
55 |
+
"temperature": 1.0,
|
56 |
+
"top_k": 1,
|
57 |
+
"top_p": 1.0
|
58 |
+
}
|
59 |
+
}
|
cuda/cuda-int4-awq-block-128/phi3-mini-4k-instruct-cuda-int4-awq-block-128.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a4b2cdae4b3d3efa98a2909c349ceeb470a29d4d9125cc75cbf1bcbfeeff9db
|
3 |
+
size 261201
|
cuda/cuda-int4-awq-block-128/phi3-mini-4k-instruct-cuda-int4-awq-block-128.onnx.data
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be23af338e40feaf91a29fa937e85a6d6879b3e56c278c3e1a7f859a6a846000
|
3 |
+
size 2277906432
|
cuda/cuda-int4-awq-block-128/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
cuda/cuda-int4-awq-block-128/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
cuda/cuda-int4-awq-block-128/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
cuda/cuda-int4-awq-block-128/tokenizer_config.json
ADDED
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": true,
|
26 |
+
"single_word": false,
|
27 |
+
"special": false
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "<|endoftext|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"32001": {
|
38 |
+
"content": "<|assistant|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": true,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"32002": {
|
46 |
+
"content": "<|placeholder1|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": true,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"32003": {
|
54 |
+
"content": "<|placeholder2|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": true,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"32004": {
|
62 |
+
"content": "<|placeholder3|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": true,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"32005": {
|
70 |
+
"content": "<|placeholder4|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": true,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"32006": {
|
78 |
+
"content": "<|system|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": true,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"32007": {
|
86 |
+
"content": "<|end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": true,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"32008": {
|
94 |
+
"content": "<|placeholder5|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": true,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"32009": {
|
102 |
+
"content": "<|placeholder6|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": true,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"32010": {
|
110 |
+
"content": "<|user|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": true,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
}
|
117 |
+
},
|
118 |
+
"bos_token": "<s>",
|
119 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
|
120 |
+
"clean_up_tokenization_spaces": false,
|
121 |
+
"eos_token": "<|endoftext|>",
|
122 |
+
"legacy": false,
|
123 |
+
"model_max_length": 4096,
|
124 |
+
"pad_token": "<|endoftext|>",
|
125 |
+
"padding_side": "left",
|
126 |
+
"sp_model_kwargs": {},
|
127 |
+
"tokenizer_class": "LlamaTokenizer",
|
128 |
+
"unk_token": "<unk>",
|
129 |
+
"use_default_system_prompt": false
|
130 |
+
}
|
cuda/cuda-int4-rtn-block-32/added_tokens.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
-
{
|
2 |
-
"<|endoftext|>": 32000,
|
3 |
-
"<|assistant|>": 32001,
|
4 |
-
"<|placeholder1|>": 32002,
|
5 |
-
"<|placeholder2|>": 32003,
|
6 |
-
"<|placeholder3|>": 32004,
|
7 |
-
"<|placeholder4|>": 32005,
|
8 |
-
"<|system|>": 32006,
|
9 |
-
"<|end|>": 32007,
|
10 |
-
"<|placeholder5|>": 32008,
|
11 |
-
"<|placeholder6|>": 32009,
|
12 |
-
"<|user|>": 32010
|
13 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 32000,
|
3 |
+
"<|assistant|>": 32001,
|
4 |
+
"<|placeholder1|>": 32002,
|
5 |
+
"<|placeholder2|>": 32003,
|
6 |
+
"<|placeholder3|>": 32004,
|
7 |
+
"<|placeholder4|>": 32005,
|
8 |
+
"<|system|>": 32006,
|
9 |
+
"<|end|>": 32007,
|
10 |
+
"<|placeholder5|>": 32008,
|
11 |
+
"<|placeholder6|>": 32009,
|
12 |
+
"<|user|>": 32010
|
13 |
+
}
|
cuda/cuda-int4-rtn-block-32/config.json
CHANGED
@@ -1,35 +1,36 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"architectures": [
|
4 |
-
"Phi3ForCausalLM"
|
5 |
-
],
|
6 |
-
"attention_dropout": 0.0,
|
7 |
-
"auto_map": {
|
8 |
-
"AutoConfig": "configuration_phi3.Phi3Config",
|
9 |
-
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
|
10 |
-
},
|
11 |
-
"bos_token_id": 1,
|
12 |
-
"embd_pdrop": 0.0,
|
13 |
-
"eos_token_id": 32000,
|
14 |
-
"hidden_act": "silu",
|
15 |
-
"hidden_size": 3072,
|
16 |
-
"initializer_range": 0.02,
|
17 |
-
"intermediate_size": 8192,
|
18 |
-
"max_position_embeddings": 4096,
|
19 |
-
"model_type": "phi3",
|
20 |
-
"num_attention_heads": 32,
|
21 |
-
"num_hidden_layers": 32,
|
22 |
-
"num_key_value_heads": 32,
|
23 |
-
"original_max_position_embeddings": 4096,
|
24 |
-
"pad_token_id": 32000,
|
25 |
-
"resid_pdrop": 0.0,
|
26 |
-
"rms_norm_eps": 1e-05,
|
27 |
-
"rope_scaling": null,
|
28 |
-
"rope_theta": 10000.0,
|
29 |
-
"sliding_window": 2047,
|
30 |
-
"tie_word_embeddings": false,
|
31 |
-
"torch_dtype": "bfloat16",
|
32 |
-
"transformers_version": "4.
|
33 |
-
"use_cache": true,
|
34 |
-
"
|
35 |
-
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Phi-3-mini-4k-instruct",
|
3 |
+
"architectures": [
|
4 |
+
"Phi3ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"auto_map": {
|
8 |
+
"AutoConfig": "configuration_phi3.Phi3Config",
|
9 |
+
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
|
10 |
+
},
|
11 |
+
"bos_token_id": 1,
|
12 |
+
"embd_pdrop": 0.0,
|
13 |
+
"eos_token_id": 32000,
|
14 |
+
"hidden_act": "silu",
|
15 |
+
"hidden_size": 3072,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 8192,
|
18 |
+
"max_position_embeddings": 4096,
|
19 |
+
"model_type": "phi3",
|
20 |
+
"num_attention_heads": 32,
|
21 |
+
"num_hidden_layers": 32,
|
22 |
+
"num_key_value_heads": 32,
|
23 |
+
"original_max_position_embeddings": 4096,
|
24 |
+
"pad_token_id": 32000,
|
25 |
+
"resid_pdrop": 0.0,
|
26 |
+
"rms_norm_eps": 1e-05,
|
27 |
+
"rope_scaling": null,
|
28 |
+
"rope_theta": 10000.0,
|
29 |
+
"sliding_window": 2047,
|
30 |
+
"tie_word_embeddings": false,
|
31 |
+
"torch_dtype": "bfloat16",
|
32 |
+
"transformers_version": "4.40.2",
|
33 |
+
"use_cache": true,
|
34 |
+
"attention_bias": false,
|
35 |
+
"vocab_size": 32064
|
36 |
+
}
|
cuda/cuda-int4-rtn-block-32/configuration_phi3.py
CHANGED
@@ -1,213 +1,227 @@
|
|
1 |
-
# coding=utf-8
|
2 |
-
# Copyright 2024 Microsoft and the HuggingFace Inc. team. All rights reserved.
|
3 |
-
#
|
4 |
-
# Licensed under the Apache License, Version 2.0 (the "License");
|
5 |
-
# you may not use this file except in compliance with the License.
|
6 |
-
# You may obtain a copy of the License at
|
7 |
-
#
|
8 |
-
# http://www.apache.org/licenses/LICENSE-2.0
|
9 |
-
#
|
10 |
-
# Unless required by applicable law or agreed to in writing, software
|
11 |
-
# distributed under the License is distributed on an "AS IS" BASIS,
|
12 |
-
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
13 |
-
# See the License for the specific language governing permissions and
|
14 |
-
# limitations under the License.
|
15 |
-
|
16 |
-
""" Phi-3 model configuration"""
|
17 |
-
|
18 |
-
|
19 |
-
from transformers.configuration_utils import PretrainedConfig
|
20 |
-
from transformers.utils import logging
|
21 |
-
|
22 |
-
|
23 |
-
logger = logging.get_logger(__name__)
|
24 |
-
|
25 |
-
PHI3_PRETRAINED_CONFIG_ARCHIVE_MAP = {
|
26 |
-
"microsoft/Phi-3-mini-4k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/resolve/main/config.json",
|
27 |
-
"microsoft/Phi-3-mini-128k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/config.json",
|
28 |
-
}
|
29 |
-
|
30 |
-
|
31 |
-
class Phi3Config(PretrainedConfig):
|
32 |
-
r"""
|
33 |
-
This is the configuration class to store the configuration of a [`Phi3Model`]. It is used to instantiate a Phi-3
|
34 |
-
model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
|
35 |
-
defaults will yield a similar configuration to that of the
|
36 |
-
[microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct).
|
37 |
-
|
38 |
-
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
|
39 |
-
documentation from [`PretrainedConfig`] for more information.
|
40 |
-
|
41 |
-
Args:
|
42 |
-
vocab_size (`int`, *optional*, defaults to 32064):
|
43 |
-
Vocabulary size of the Phi-3 model. Defines the number of different tokens that can be represented by the
|
44 |
-
`inputs_ids` passed when calling [`Phi3Model`].
|
45 |
-
hidden_size (`int`, *optional*, defaults to 3072):
|
46 |
-
Dimension of the hidden representations.
|
47 |
-
intermediate_size (`int`, *optional*, defaults to 8192):
|
48 |
-
Dimension of the MLP representations.
|
49 |
-
num_hidden_layers (`int`, *optional*, defaults to 32):
|
50 |
-
Number of hidden layers in the Transformer decoder.
|
51 |
-
num_attention_heads (`int`, *optional*, defaults to 32):
|
52 |
-
Number of attention heads for each attention layer in the Transformer decoder.
|
53 |
-
num_key_value_heads (`int`, *optional*):
|
54 |
-
This is the number of key_value heads that should be used to implement Grouped Query Attention. If
|
55 |
-
`num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
|
56 |
-
`num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
|
57 |
-
converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
|
58 |
-
by meanpooling all the original heads within that group. For more details checkout [this
|
59 |
-
paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
|
60 |
-
`num_attention_heads`.
|
61 |
-
resid_pdrop (`float`, *optional*, defaults to 0.0):
|
62 |
-
Dropout probability for mlp outputs.
|
63 |
-
embd_pdrop (`int`, *optional*, defaults to 0.0):
|
64 |
-
The dropout ratio for the embeddings.
|
65 |
-
attention_dropout (`float`, *optional*, defaults to 0.0):
|
66 |
-
The dropout ratio after computing the attention scores.
|
67 |
-
hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
|
68 |
-
The non-linear activation function (function or string) in the decoder.
|
69 |
-
max_position_embeddings (`int`, *optional*, defaults to 4096):
|
70 |
-
The maximum sequence length that this model might ever be used with.
|
71 |
-
original_max_position_embeddings (`int`, *optional*, defaults to 4096):
|
72 |
-
The maximum sequence length that this model was trained with. This is used to determine the size of the
|
73 |
-
original RoPE embeddings when using long scaling.
|
74 |
-
initializer_range (`float`, *optional*, defaults to 0.02):
|
75 |
-
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
|
76 |
-
rms_norm_eps (`float`, *optional*, defaults to 1e-05):
|
77 |
-
The epsilon value used for the RMSNorm.
|
78 |
-
use_cache (`bool`, *optional*, defaults to `True`):
|
79 |
-
Whether or not the model should return the last key/values attentions (not used by all models). Only
|
80 |
-
relevant if `config.is_decoder=True`. Whether to tie weight embeddings or not.
|
81 |
-
tie_word_embeddings (`bool`, *optional*, defaults to `False`):
|
82 |
-
Whether to tie weight embeddings
|
83 |
-
rope_theta (`float`, *optional*, defaults to 10000.0):
|
84 |
-
The base period of the RoPE embeddings.
|
85 |
-
rope_scaling (`dict`, *optional*):
|
86 |
-
The scaling strategy for the RoPE embeddings. If `None`, no scaling is applied. If a dictionary, it must
|
87 |
-
contain the following keys: `type`, `short_factor` and `long_factor`. The `type` must be
|
88 |
-
the `short_factor` and `long_factor` must be lists of numbers with the same length as the hidden size
|
89 |
-
divided by the number of attention heads divided by 2.
|
90 |
-
bos_token_id (`int`, *optional*, defaults to 1):
|
91 |
-
The id of the "beginning-of-sequence" token.
|
92 |
-
eos_token_id (`int`, *optional*, defaults to 32000):
|
93 |
-
The id of the "end-of-sequence" token.
|
94 |
-
pad_token_id (`int`, *optional*, defaults to 32000):
|
95 |
-
The id of the padding token.
|
96 |
-
sliding_window (`int`, *optional*):
|
97 |
-
Sliding window attention window size. If `None`, no sliding window is applied.
|
98 |
-
|
99 |
-
Example:
|
100 |
-
|
101 |
-
```python
|
102 |
-
>>> from transformers import Phi3Model, Phi3Config
|
103 |
-
|
104 |
-
>>> # Initializing a Phi-3 style configuration
|
105 |
-
>>> configuration = Phi3Config.from_pretrained("microsoft/Phi-3-mini-4k-instruct")
|
106 |
-
|
107 |
-
>>> # Initializing a model from the configuration
|
108 |
-
>>> model = Phi3Model(configuration)
|
109 |
-
|
110 |
-
>>> # Accessing the model configuration
|
111 |
-
>>> configuration = model.config
|
112 |
-
```"""
|
113 |
-
|
114 |
-
model_type = "phi3"
|
115 |
-
keys_to_ignore_at_inference = ["past_key_values"]
|
116 |
-
|
117 |
-
def __init__(
|
118 |
-
self,
|
119 |
-
vocab_size=32064,
|
120 |
-
hidden_size=3072,
|
121 |
-
intermediate_size=8192,
|
122 |
-
num_hidden_layers=32,
|
123 |
-
num_attention_heads=32,
|
124 |
-
num_key_value_heads=None,
|
125 |
-
resid_pdrop=0.0,
|
126 |
-
embd_pdrop=0.0,
|
127 |
-
attention_dropout=0.0,
|
128 |
-
hidden_act="silu",
|
129 |
-
max_position_embeddings=4096,
|
130 |
-
original_max_position_embeddings=4096,
|
131 |
-
initializer_range=0.02,
|
132 |
-
rms_norm_eps=1e-5,
|
133 |
-
use_cache=True,
|
134 |
-
tie_word_embeddings=False,
|
135 |
-
rope_theta=10000.0,
|
136 |
-
rope_scaling=None,
|
137 |
-
bos_token_id=1,
|
138 |
-
eos_token_id=32000,
|
139 |
-
pad_token_id=32000,
|
140 |
-
sliding_window=None,
|
141 |
-
**kwargs,
|
142 |
-
):
|
143 |
-
self.vocab_size = vocab_size
|
144 |
-
self.hidden_size = hidden_size
|
145 |
-
self.intermediate_size = intermediate_size
|
146 |
-
self.num_hidden_layers = num_hidden_layers
|
147 |
-
self.num_attention_heads = num_attention_heads
|
148 |
-
|
149 |
-
if num_key_value_heads is None:
|
150 |
-
num_key_value_heads = num_attention_heads
|
151 |
-
|
152 |
-
self.num_key_value_heads = num_key_value_heads
|
153 |
-
self.resid_pdrop = resid_pdrop
|
154 |
-
self.embd_pdrop = embd_pdrop
|
155 |
-
self.attention_dropout = attention_dropout
|
156 |
-
self.hidden_act = hidden_act
|
157 |
-
self.max_position_embeddings = max_position_embeddings
|
158 |
-
self.original_max_position_embeddings = original_max_position_embeddings
|
159 |
-
self.initializer_range = initializer_range
|
160 |
-
self.rms_norm_eps = rms_norm_eps
|
161 |
-
self.use_cache = use_cache
|
162 |
-
self.rope_theta = rope_theta
|
163 |
-
self.rope_scaling = rope_scaling
|
164 |
-
self.
|
165 |
-
self.
|
166 |
-
|
167 |
-
|
168 |
-
|
169 |
-
|
170 |
-
|
171 |
-
|
172 |
-
|
173 |
-
|
174 |
-
|
175 |
-
|
176 |
-
|
177 |
-
|
178 |
-
|
179 |
-
|
180 |
-
|
181 |
-
|
182 |
-
|
183 |
-
|
184 |
-
|
185 |
-
|
186 |
-
|
187 |
-
|
188 |
-
|
189 |
-
|
190 |
-
|
191 |
-
|
192 |
-
|
193 |
-
|
194 |
-
|
195 |
-
|
196 |
-
|
197 |
-
|
198 |
-
|
199 |
-
|
200 |
-
|
201 |
-
|
202 |
-
|
203 |
-
|
204 |
-
|
205 |
-
|
206 |
-
|
207 |
-
|
208 |
-
|
209 |
-
|
210 |
-
|
211 |
-
|
212 |
-
|
213 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# coding=utf-8
|
2 |
+
# Copyright 2024 Microsoft and the HuggingFace Inc. team. All rights reserved.
|
3 |
+
#
|
4 |
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
5 |
+
# you may not use this file except in compliance with the License.
|
6 |
+
# You may obtain a copy of the License at
|
7 |
+
#
|
8 |
+
# http://www.apache.org/licenses/LICENSE-2.0
|
9 |
+
#
|
10 |
+
# Unless required by applicable law or agreed to in writing, software
|
11 |
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
12 |
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
13 |
+
# See the License for the specific language governing permissions and
|
14 |
+
# limitations under the License.
|
15 |
+
|
16 |
+
""" Phi-3 model configuration"""
|
17 |
+
|
18 |
+
|
19 |
+
from transformers.configuration_utils import PretrainedConfig
|
20 |
+
from transformers.utils import logging
|
21 |
+
|
22 |
+
|
23 |
+
logger = logging.get_logger(__name__)
|
24 |
+
|
25 |
+
PHI3_PRETRAINED_CONFIG_ARCHIVE_MAP = {
|
26 |
+
"microsoft/Phi-3-mini-4k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/resolve/main/config.json",
|
27 |
+
"microsoft/Phi-3-mini-128k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/config.json",
|
28 |
+
}
|
29 |
+
|
30 |
+
|
31 |
+
class Phi3Config(PretrainedConfig):
|
32 |
+
r"""
|
33 |
+
This is the configuration class to store the configuration of a [`Phi3Model`]. It is used to instantiate a Phi-3
|
34 |
+
model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
|
35 |
+
defaults will yield a similar configuration to that of the
|
36 |
+
[microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct).
|
37 |
+
|
38 |
+
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
|
39 |
+
documentation from [`PretrainedConfig`] for more information.
|
40 |
+
|
41 |
+
Args:
|
42 |
+
vocab_size (`int`, *optional*, defaults to 32064):
|
43 |
+
Vocabulary size of the Phi-3 model. Defines the number of different tokens that can be represented by the
|
44 |
+
`inputs_ids` passed when calling [`Phi3Model`].
|
45 |
+
hidden_size (`int`, *optional*, defaults to 3072):
|
46 |
+
Dimension of the hidden representations.
|
47 |
+
intermediate_size (`int`, *optional*, defaults to 8192):
|
48 |
+
Dimension of the MLP representations.
|
49 |
+
num_hidden_layers (`int`, *optional*, defaults to 32):
|
50 |
+
Number of hidden layers in the Transformer decoder.
|
51 |
+
num_attention_heads (`int`, *optional*, defaults to 32):
|
52 |
+
Number of attention heads for each attention layer in the Transformer decoder.
|
53 |
+
num_key_value_heads (`int`, *optional*):
|
54 |
+
This is the number of key_value heads that should be used to implement Grouped Query Attention. If
|
55 |
+
`num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
|
56 |
+
`num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
|
57 |
+
converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
|
58 |
+
by meanpooling all the original heads within that group. For more details checkout [this
|
59 |
+
paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
|
60 |
+
`num_attention_heads`.
|
61 |
+
resid_pdrop (`float`, *optional*, defaults to 0.0):
|
62 |
+
Dropout probability for mlp outputs.
|
63 |
+
embd_pdrop (`int`, *optional*, defaults to 0.0):
|
64 |
+
The dropout ratio for the embeddings.
|
65 |
+
attention_dropout (`float`, *optional*, defaults to 0.0):
|
66 |
+
The dropout ratio after computing the attention scores.
|
67 |
+
hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
|
68 |
+
The non-linear activation function (function or string) in the decoder.
|
69 |
+
max_position_embeddings (`int`, *optional*, defaults to 4096):
|
70 |
+
The maximum sequence length that this model might ever be used with.
|
71 |
+
original_max_position_embeddings (`int`, *optional*, defaults to 4096):
|
72 |
+
The maximum sequence length that this model was trained with. This is used to determine the size of the
|
73 |
+
original RoPE embeddings when using long scaling.
|
74 |
+
initializer_range (`float`, *optional*, defaults to 0.02):
|
75 |
+
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
|
76 |
+
rms_norm_eps (`float`, *optional*, defaults to 1e-05):
|
77 |
+
The epsilon value used for the RMSNorm.
|
78 |
+
use_cache (`bool`, *optional*, defaults to `True`):
|
79 |
+
Whether or not the model should return the last key/values attentions (not used by all models). Only
|
80 |
+
relevant if `config.is_decoder=True`. Whether to tie weight embeddings or not.
|
81 |
+
tie_word_embeddings (`bool`, *optional*, defaults to `False`):
|
82 |
+
Whether to tie weight embeddings
|
83 |
+
rope_theta (`float`, *optional*, defaults to 10000.0):
|
84 |
+
The base period of the RoPE embeddings.
|
85 |
+
rope_scaling (`dict`, *optional*):
|
86 |
+
The scaling strategy for the RoPE embeddings. If `None`, no scaling is applied. If a dictionary, it must
|
87 |
+
contain the following keys: `type`, `short_factor` and `long_factor`. The `type` must be `longrope` and
|
88 |
+
the `short_factor` and `long_factor` must be lists of numbers with the same length as the hidden size
|
89 |
+
divided by the number of attention heads divided by 2.
|
90 |
+
bos_token_id (`int`, *optional*, defaults to 1):
|
91 |
+
The id of the "beginning-of-sequence" token.
|
92 |
+
eos_token_id (`int`, *optional*, defaults to 32000):
|
93 |
+
The id of the "end-of-sequence" token.
|
94 |
+
pad_token_id (`int`, *optional*, defaults to 32000):
|
95 |
+
The id of the padding token.
|
96 |
+
sliding_window (`int`, *optional*):
|
97 |
+
Sliding window attention window size. If `None`, no sliding window is applied.
|
98 |
+
|
99 |
+
Example:
|
100 |
+
|
101 |
+
```python
|
102 |
+
>>> from transformers import Phi3Model, Phi3Config
|
103 |
+
|
104 |
+
>>> # Initializing a Phi-3 style configuration
|
105 |
+
>>> configuration = Phi3Config.from_pretrained("microsoft/Phi-3-mini-4k-instruct")
|
106 |
+
|
107 |
+
>>> # Initializing a model from the configuration
|
108 |
+
>>> model = Phi3Model(configuration)
|
109 |
+
|
110 |
+
>>> # Accessing the model configuration
|
111 |
+
>>> configuration = model.config
|
112 |
+
```"""
|
113 |
+
|
114 |
+
model_type = "phi3"
|
115 |
+
keys_to_ignore_at_inference = ["past_key_values"]
|
116 |
+
|
117 |
+
def __init__(
|
118 |
+
self,
|
119 |
+
vocab_size=32064,
|
120 |
+
hidden_size=3072,
|
121 |
+
intermediate_size=8192,
|
122 |
+
num_hidden_layers=32,
|
123 |
+
num_attention_heads=32,
|
124 |
+
num_key_value_heads=None,
|
125 |
+
resid_pdrop=0.0,
|
126 |
+
embd_pdrop=0.0,
|
127 |
+
attention_dropout=0.0,
|
128 |
+
hidden_act="silu",
|
129 |
+
max_position_embeddings=4096,
|
130 |
+
original_max_position_embeddings=4096,
|
131 |
+
initializer_range=0.02,
|
132 |
+
rms_norm_eps=1e-5,
|
133 |
+
use_cache=True,
|
134 |
+
tie_word_embeddings=False,
|
135 |
+
rope_theta=10000.0,
|
136 |
+
rope_scaling=None,
|
137 |
+
bos_token_id=1,
|
138 |
+
eos_token_id=32000,
|
139 |
+
pad_token_id=32000,
|
140 |
+
sliding_window=None,
|
141 |
+
**kwargs,
|
142 |
+
):
|
143 |
+
self.vocab_size = vocab_size
|
144 |
+
self.hidden_size = hidden_size
|
145 |
+
self.intermediate_size = intermediate_size
|
146 |
+
self.num_hidden_layers = num_hidden_layers
|
147 |
+
self.num_attention_heads = num_attention_heads
|
148 |
+
|
149 |
+
if num_key_value_heads is None:
|
150 |
+
num_key_value_heads = num_attention_heads
|
151 |
+
|
152 |
+
self.num_key_value_heads = num_key_value_heads
|
153 |
+
self.resid_pdrop = resid_pdrop
|
154 |
+
self.embd_pdrop = embd_pdrop
|
155 |
+
self.attention_dropout = attention_dropout
|
156 |
+
self.hidden_act = hidden_act
|
157 |
+
self.max_position_embeddings = max_position_embeddings
|
158 |
+
self.original_max_position_embeddings = original_max_position_embeddings
|
159 |
+
self.initializer_range = initializer_range
|
160 |
+
self.rms_norm_eps = rms_norm_eps
|
161 |
+
self.use_cache = use_cache
|
162 |
+
self.rope_theta = rope_theta
|
163 |
+
self.rope_scaling = rope_scaling
|
164 |
+
self._rope_scaling_adjustment()
|
165 |
+
self._rope_scaling_validation()
|
166 |
+
self.sliding_window = sliding_window
|
167 |
+
|
168 |
+
super().__init__(
|
169 |
+
bos_token_id=bos_token_id,
|
170 |
+
eos_token_id=eos_token_id,
|
171 |
+
pad_token_id=pad_token_id,
|
172 |
+
tie_word_embeddings=tie_word_embeddings,
|
173 |
+
**kwargs,
|
174 |
+
)
|
175 |
+
|
176 |
+
def _rope_scaling_adjustment(self):
|
177 |
+
"""
|
178 |
+
Adjust the `type` of the `rope_scaling` configuration for backward compatibility.
|
179 |
+
"""
|
180 |
+
if self.rope_scaling is None:
|
181 |
+
return
|
182 |
+
|
183 |
+
rope_scaling_type = self.rope_scaling.get("type", None)
|
184 |
+
|
185 |
+
# For backward compatibility if previous version used "su" or "yarn"
|
186 |
+
if rope_scaling_type is not None and rope_scaling_type in ["su", "yarn"]:
|
187 |
+
self.rope_scaling["type"] = "longrope"
|
188 |
+
|
189 |
+
def _rope_scaling_validation(self):
|
190 |
+
"""
|
191 |
+
Validate the `rope_scaling` configuration.
|
192 |
+
"""
|
193 |
+
if self.rope_scaling is None:
|
194 |
+
return
|
195 |
+
|
196 |
+
if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 3:
|
197 |
+
raise ValueError(
|
198 |
+
"`rope_scaling` must be a dictionary with three fields, `type`, `short_factor` and `long_factor`, "
|
199 |
+
f"got {self.rope_scaling}"
|
200 |
+
)
|
201 |
+
rope_scaling_type = self.rope_scaling.get("type", None)
|
202 |
+
rope_scaling_short_factor = self.rope_scaling.get("short_factor", None)
|
203 |
+
rope_scaling_long_factor = self.rope_scaling.get("long_factor", None)
|
204 |
+
if rope_scaling_type is None or rope_scaling_type not in ["longrope"]:
|
205 |
+
raise ValueError(f"`rope_scaling`'s type field must be one of ['longrope'], got {rope_scaling_type}")
|
206 |
+
if not (
|
207 |
+
isinstance(rope_scaling_short_factor, list)
|
208 |
+
and all(isinstance(x, (int, float)) for x in rope_scaling_short_factor)
|
209 |
+
):
|
210 |
+
raise ValueError(
|
211 |
+
f"`rope_scaling`'s short_factor field must be a list of numbers, got {rope_scaling_short_factor}"
|
212 |
+
)
|
213 |
+
if not len(rope_scaling_short_factor) == self.hidden_size // self.num_attention_heads // 2:
|
214 |
+
raise ValueError(
|
215 |
+
f"`rope_scaling`'s short_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_short_factor)}"
|
216 |
+
)
|
217 |
+
if not (
|
218 |
+
isinstance(rope_scaling_long_factor, list)
|
219 |
+
and all(isinstance(x, (int, float)) for x in rope_scaling_long_factor)
|
220 |
+
):
|
221 |
+
raise ValueError(
|
222 |
+
f"`rope_scaling`'s long_factor field must be a list of numbers, got {rope_scaling_long_factor}"
|
223 |
+
)
|
224 |
+
if not len(rope_scaling_long_factor) == self.hidden_size // self.num_attention_heads // 2:
|
225 |
+
raise ValueError(
|
226 |
+
f"`rope_scaling`'s long_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_long_factor)}"
|
227 |
+
)
|
cuda/cuda-int4-rtn-block-32/genai_config.json
CHANGED
@@ -56,4 +56,4 @@
|
|
56 |
"top_k": 1,
|
57 |
"top_p": 1.0
|
58 |
}
|
59 |
-
}
|
|
|
56 |
"top_k": 1,
|
57 |
"top_p": 1.0
|
58 |
}
|
59 |
+
}
|
cuda/cuda-int4-rtn-block-32/phi3-mini-4k-instruct-cuda-int4-rtn-block-32.onnx.data
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2292025344
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b05e2aa951df379a6c155b7bec5c3cd66e04a351c80fc25a66d0616d180e50d5
|
3 |
size 2292025344
|
cuda/cuda-int4-rtn-block-32/special_tokens_map.json
CHANGED
@@ -1,30 +1,30 @@
|
|
1 |
-
{
|
2 |
-
"bos_token": {
|
3 |
-
"content": "<s>",
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": false,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"eos_token": {
|
10 |
-
"content": "<|endoftext|>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"pad_token": {
|
17 |
-
"content": "<|endoftext|>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"unk_token": {
|
24 |
-
"content": "<unk>",
|
25 |
-
"lstrip": false,
|
26 |
-
"normalized": false,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
}
|
30 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|