Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- config.json +60 -0
- configuration_deepseek.py +206 -0
- generation_config.json +9 -0
- model-00001-of-000055.safetensors +3 -0
- model-00002-of-000055.safetensors +3 -0
- model-00003-of-000055.safetensors +3 -0
- model-00004-of-000055.safetensors +3 -0
- model-00005-of-000055.safetensors +3 -0
- model-00006-of-000055.safetensors +3 -0
- model-00007-of-000055.safetensors +3 -0
- model-00008-of-000055.safetensors +3 -0
- model-00009-of-000055.safetensors +3 -0
- model-00010-of-000055.safetensors +3 -0
- model-00011-of-000055.safetensors +3 -0
- model-00012-of-000055.safetensors +3 -0
- model-00013-of-000055.safetensors +3 -0
- model-00014-of-000055.safetensors +3 -0
- model-00015-of-000055.safetensors +3 -0
- model-00016-of-000055.safetensors +3 -0
- model-00017-of-000055.safetensors +3 -0
- model-00018-of-000055.safetensors +3 -0
- model-00019-of-000055.safetensors +3 -0
- model-00020-of-000055.safetensors +3 -0
- model-00021-of-000055.safetensors +3 -0
- model-00022-of-000055.safetensors +3 -0
- model-00023-of-000055.safetensors +3 -0
- model-00024-of-000055.safetensors +3 -0
- model-00025-of-000055.safetensors +3 -0
- model-00026-of-000055.safetensors +3 -0
- model-00027-of-000055.safetensors +3 -0
- model-00028-of-000055.safetensors +3 -0
- model-00029-of-000055.safetensors +3 -0
- model-00030-of-000055.safetensors +3 -0
- model-00031-of-000055.safetensors +3 -0
- model-00032-of-000055.safetensors +3 -0
- model-00033-of-000055.safetensors +3 -0
- model-00034-of-000055.safetensors +3 -0
- model-00035-of-000055.safetensors +3 -0
- model-00036-of-000055.safetensors +3 -0
- model-00037-of-000055.safetensors +3 -0
- model-00038-of-000055.safetensors +3 -0
- model-00039-of-000055.safetensors +3 -0
- model-00040-of-000055.safetensors +3 -0
- model-00041-of-000055.safetensors +3 -0
- model-00042-of-000055.safetensors +3 -0
- model-00043-of-000055.safetensors +3 -0
- model-00044-of-000055.safetensors +3 -0
- model-00045-of-000055.safetensors +3 -0
- model-00046-of-000055.safetensors +3 -0
- model-00047-of-000055.safetensors +3 -0
config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"DeepseekV2ForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_bias": false,
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"auto_map": {
|
8 |
+
"AutoConfig": "configuration_deepseek.DeepseekV2Config",
|
9 |
+
"AutoModel": "modeling_deepseek.DeepseekV2Model",
|
10 |
+
"AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM"
|
11 |
+
},
|
12 |
+
"aux_loss_alpha": 0.001,
|
13 |
+
"bos_token_id": 100000,
|
14 |
+
"eos_token_id": 100001,
|
15 |
+
"ep_size": 1,
|
16 |
+
"first_k_dense_replace": 1,
|
17 |
+
"hidden_act": "silu",
|
18 |
+
"hidden_size": 5120,
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 12288,
|
21 |
+
"kv_lora_rank": 512,
|
22 |
+
"max_position_embeddings": 163840,
|
23 |
+
"model_type": "deepseek_v2",
|
24 |
+
"moe_intermediate_size": 1536,
|
25 |
+
"moe_layer_freq": 1,
|
26 |
+
"n_group": 8,
|
27 |
+
"n_routed_experts": 160,
|
28 |
+
"n_shared_experts": 2,
|
29 |
+
"norm_topk_prob": false,
|
30 |
+
"num_attention_heads": 128,
|
31 |
+
"num_experts_per_tok": 6,
|
32 |
+
"num_hidden_layers": 60,
|
33 |
+
"num_key_value_heads": 128,
|
34 |
+
"pretraining_tp": 1,
|
35 |
+
"q_lora_rank": 1536,
|
36 |
+
"qk_nope_head_dim": 128,
|
37 |
+
"qk_rope_head_dim": 64,
|
38 |
+
"rms_norm_eps": 1e-06,
|
39 |
+
"rope_scaling": {
|
40 |
+
"beta_fast": 32,
|
41 |
+
"beta_slow": 1,
|
42 |
+
"factor": 40,
|
43 |
+
"mscale": 1.0,
|
44 |
+
"mscale_all_dim": 1.0,
|
45 |
+
"original_max_position_embeddings": 4096,
|
46 |
+
"type": "yarn"
|
47 |
+
},
|
48 |
+
"rope_theta": 10000,
|
49 |
+
"routed_scaling_factor": 16.0,
|
50 |
+
"scoring_func": "softmax",
|
51 |
+
"seq_aux": true,
|
52 |
+
"tie_word_embeddings": false,
|
53 |
+
"topk_group": 3,
|
54 |
+
"topk_method": "group_limited_greedy",
|
55 |
+
"torch_dtype": "bfloat16",
|
56 |
+
"transformers_version": "4.39.3",
|
57 |
+
"use_cache": true,
|
58 |
+
"v_head_dim": 128,
|
59 |
+
"vocab_size": 102400
|
60 |
+
}
|
configuration_deepseek.py
ADDED
@@ -0,0 +1,206 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from transformers.configuration_utils import PretrainedConfig
|
2 |
+
from transformers.utils import logging
|
3 |
+
|
4 |
+
logger = logging.get_logger(__name__)
|
5 |
+
|
6 |
+
DEEPSEEK_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
|
7 |
+
class DeepseekV2Config(PretrainedConfig):
|
8 |
+
r"""
|
9 |
+
This is the configuration class to store the configuration of a [`DeepseekV2Model`]. It is used to instantiate an DeepSeek
|
10 |
+
model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
|
11 |
+
defaults will yield a similar configuration to that of the DeepSeek-V2.
|
12 |
+
|
13 |
+
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
|
14 |
+
documentation from [`PretrainedConfig`] for more information.
|
15 |
+
|
16 |
+
|
17 |
+
Args:
|
18 |
+
vocab_size (`int`, *optional*, defaults to 102400):
|
19 |
+
Vocabulary size of the Deep model. Defines the number of different tokens that can be represented by the
|
20 |
+
`inputs_ids` passed when calling [`DeepseekV2Model`]
|
21 |
+
hidden_size (`int`, *optional*, defaults to 4096):
|
22 |
+
Dimension of the hidden representations.
|
23 |
+
intermediate_size (`int`, *optional*, defaults to 11008):
|
24 |
+
Dimension of the MLP representations.
|
25 |
+
moe_intermediate_size (`int`, *optional*, defaults to 1407):
|
26 |
+
Dimension of the MoE representations.
|
27 |
+
num_hidden_layers (`int`, *optional*, defaults to 32):
|
28 |
+
Number of hidden layers in the Transformer decoder.
|
29 |
+
num_attention_heads (`int`, *optional*, defaults to 32):
|
30 |
+
Number of attention heads for each attention layer in the Transformer decoder.
|
31 |
+
n_shared_experts (`int`, *optional*, defaults to None):
|
32 |
+
Number of shared experts, None means dense model.
|
33 |
+
n_routed_experts (`int`, *optional*, defaults to None):
|
34 |
+
Number of routed experts, None means dense model.
|
35 |
+
routed_scaling_factor (`float`, *optional*, defaults to 1.0):
|
36 |
+
Scaling factor or routed experts.
|
37 |
+
topk_method (`str`, *optional*, defaults to `gready`):
|
38 |
+
Topk method used in routed gate.
|
39 |
+
n_group (`int`, *optional*, defaults to None):
|
40 |
+
Number of groups for routed experts.
|
41 |
+
topk_group (`int`, *optional*, defaults to None):
|
42 |
+
Number of selected groups for each token(for each token, ensuring the selected experts is only within `topk_group` groups).
|
43 |
+
num_experts_per_tok (`int`, *optional*, defaults to None):
|
44 |
+
Number of selected experts, None means dense model.
|
45 |
+
moe_layer_freq (`int`, *optional*, defaults to 1):
|
46 |
+
The frequency of the MoE layer: one expert layer for every `moe_layer_freq - 1` dense layers.
|
47 |
+
first_k_dense_replace (`int`, *optional*, defaults to 0):
|
48 |
+
Number of dense layers in shallow layers(embed->dense->dense->...->dense->moe->moe...->lm_head).
|
49 |
+
\--k dense layers--/
|
50 |
+
norm_topk_prob (`bool`, *optional*, defaults to False):
|
51 |
+
Whether to normalize the weights of the routed experts.
|
52 |
+
scoring_func (`str`, *optional*, defaults to 'softmax'):
|
53 |
+
Method of computing expert weights.
|
54 |
+
aux_loss_alpha (`float`, *optional*, defaults to 0.001):
|
55 |
+
Auxiliary loss weight coefficient.
|
56 |
+
seq_aux = (`bool`, *optional*, defaults to True):
|
57 |
+
Whether to compute the auxiliary loss for each individual sample.
|
58 |
+
num_key_value_heads (`int`, *optional*):
|
59 |
+
This is the number of key_value heads that should be used to implement Grouped Query Attention. If
|
60 |
+
`num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
|
61 |
+
`num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
|
62 |
+
converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
|
63 |
+
by meanpooling all the original heads within that group. For more details checkout [this
|
64 |
+
paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
|
65 |
+
`num_attention_heads`.
|
66 |
+
hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
|
67 |
+
The non-linear activation function (function or string) in the decoder.
|
68 |
+
max_position_embeddings (`int`, *optional*, defaults to 2048):
|
69 |
+
The maximum sequence length that this model might ever be used with.
|
70 |
+
initializer_range (`float`, *optional*, defaults to 0.02):
|
71 |
+
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
|
72 |
+
rms_norm_eps (`float`, *optional*, defaults to 1e-06):
|
73 |
+
The epsilon used by the rms normalization layers.
|
74 |
+
use_cache (`bool`, *optional*, defaults to `True`):
|
75 |
+
Whether or not the model should return the last key/values attentions (not used by all models). Only
|
76 |
+
relevant if `config.is_decoder=True`.
|
77 |
+
pad_token_id (`int`, *optional*):
|
78 |
+
Padding token id.
|
79 |
+
bos_token_id (`int`, *optional*, defaults to 1):
|
80 |
+
Beginning of stream token id.
|
81 |
+
eos_token_id (`int`, *optional*, defaults to 2):
|
82 |
+
End of stream token id.
|
83 |
+
pretraining_tp (`int`, *optional*, defaults to 1):
|
84 |
+
Experimental feature. Tensor parallelism rank used during pretraining. Please refer to [this
|
85 |
+
document](https://huggingface.co/docs/transformers/parallelism) to understand more about it. This value is
|
86 |
+
necessary to ensure exact reproducibility of the pretraining results. Please refer to [this
|
87 |
+
issue](https://github.com/pytorch/pytorch/issues/76232).
|
88 |
+
tie_word_embeddings (`bool`, *optional*, defaults to `False`):
|
89 |
+
Whether to tie weight embeddings
|
90 |
+
rope_theta (`float`, *optional*, defaults to 10000.0):
|
91 |
+
The base period of the RoPE embeddings.
|
92 |
+
rope_scaling (`Dict`, *optional*):
|
93 |
+
Dictionary containing the scaling configuration for the RoPE embeddings. Currently supports two scaling
|
94 |
+
strategies: linear and dynamic. Their scaling factor must be a float greater than 1. The expected format is
|
95 |
+
`{"type": strategy name, "factor": scaling factor}`. When using this flag, don't update
|
96 |
+
`max_position_embeddings` to the expected new maximum.
|
97 |
+
attention_bias (`bool`, defaults to `False`, *optional*, defaults to `False`):
|
98 |
+
Whether to use a bias in the query, key, value and output projection layers during self-attention.
|
99 |
+
attention_dropout (`float`, *optional*, defaults to 0.0):
|
100 |
+
The dropout ratio for the attention probabilities.
|
101 |
+
|
102 |
+
```python
|
103 |
+
>>> from transformers import DeepseekV2Model, DeepseekV2Config
|
104 |
+
|
105 |
+
>>> # Initializing a Deepseek-V2 style configuration
|
106 |
+
>>> configuration = DeepseekV2Config()
|
107 |
+
|
108 |
+
>>> # Accessing the model configuration
|
109 |
+
>>> configuration = model.config
|
110 |
+
```"""
|
111 |
+
|
112 |
+
model_type = "deepseek_v2"
|
113 |
+
keys_to_ignore_at_inference = ["past_key_values"]
|
114 |
+
|
115 |
+
def __init__(
|
116 |
+
self,
|
117 |
+
vocab_size=102400,
|
118 |
+
hidden_size=4096,
|
119 |
+
intermediate_size=11008,
|
120 |
+
moe_intermediate_size = 1407,
|
121 |
+
num_hidden_layers=30,
|
122 |
+
num_attention_heads=32,
|
123 |
+
num_key_value_heads=32,
|
124 |
+
n_shared_experts = None,
|
125 |
+
n_routed_experts = None,
|
126 |
+
ep_size = 1,
|
127 |
+
routed_scaling_factor = 1.0,
|
128 |
+
kv_lora_rank = 512,
|
129 |
+
q_lora_rank = 1536,
|
130 |
+
qk_rope_head_dim = 64,
|
131 |
+
v_head_dim = 128,
|
132 |
+
qk_nope_head_dim = 128,
|
133 |
+
topk_method = 'gready',
|
134 |
+
n_group = None,
|
135 |
+
topk_group = None,
|
136 |
+
num_experts_per_tok = None,
|
137 |
+
moe_layer_freq = 1,
|
138 |
+
first_k_dense_replace = 0,
|
139 |
+
norm_topk_prob = False,
|
140 |
+
scoring_func = 'softmax',
|
141 |
+
aux_loss_alpha = 0.001,
|
142 |
+
seq_aux = True,
|
143 |
+
hidden_act="silu",
|
144 |
+
max_position_embeddings=2048,
|
145 |
+
initializer_range=0.02,
|
146 |
+
rms_norm_eps=1e-6,
|
147 |
+
use_cache=True,
|
148 |
+
pad_token_id=None,
|
149 |
+
bos_token_id=100000,
|
150 |
+
eos_token_id=100001,
|
151 |
+
pretraining_tp=1,
|
152 |
+
tie_word_embeddings=False,
|
153 |
+
rope_theta=10000.0,
|
154 |
+
rope_scaling=None,
|
155 |
+
attention_bias=False,
|
156 |
+
attention_dropout=0.0,
|
157 |
+
**kwargs,
|
158 |
+
):
|
159 |
+
self.vocab_size = vocab_size
|
160 |
+
self.max_position_embeddings = max_position_embeddings
|
161 |
+
self.hidden_size = hidden_size
|
162 |
+
self.intermediate_size = intermediate_size
|
163 |
+
self.moe_intermediate_size = moe_intermediate_size
|
164 |
+
self.num_hidden_layers = num_hidden_layers
|
165 |
+
self.num_attention_heads = num_attention_heads
|
166 |
+
self.n_shared_experts = n_shared_experts
|
167 |
+
self.n_routed_experts = n_routed_experts
|
168 |
+
self.ep_size = ep_size
|
169 |
+
self.routed_scaling_factor = routed_scaling_factor
|
170 |
+
self.kv_lora_rank = kv_lora_rank
|
171 |
+
self.q_lora_rank = q_lora_rank
|
172 |
+
self.qk_rope_head_dim = qk_rope_head_dim
|
173 |
+
self.v_head_dim = v_head_dim
|
174 |
+
self.qk_nope_head_dim = qk_nope_head_dim
|
175 |
+
self.topk_method = topk_method
|
176 |
+
self.n_group = n_group
|
177 |
+
self.topk_group = topk_group
|
178 |
+
self.num_experts_per_tok = num_experts_per_tok
|
179 |
+
self.moe_layer_freq = moe_layer_freq
|
180 |
+
self.first_k_dense_replace = first_k_dense_replace
|
181 |
+
self.norm_topk_prob = norm_topk_prob
|
182 |
+
self.scoring_func = scoring_func
|
183 |
+
self.aux_loss_alpha = aux_loss_alpha
|
184 |
+
self.seq_aux = seq_aux
|
185 |
+
# for backward compatibility
|
186 |
+
if num_key_value_heads is None:
|
187 |
+
num_key_value_heads = num_attention_heads
|
188 |
+
|
189 |
+
self.num_key_value_heads = num_key_value_heads
|
190 |
+
self.hidden_act = hidden_act
|
191 |
+
self.initializer_range = initializer_range
|
192 |
+
self.rms_norm_eps = rms_norm_eps
|
193 |
+
self.pretraining_tp = pretraining_tp
|
194 |
+
self.use_cache = use_cache
|
195 |
+
self.rope_theta = rope_theta
|
196 |
+
self.rope_scaling = rope_scaling
|
197 |
+
self.attention_bias = attention_bias
|
198 |
+
self.attention_dropout = attention_dropout
|
199 |
+
|
200 |
+
super().__init__(
|
201 |
+
pad_token_id=pad_token_id,
|
202 |
+
bos_token_id=bos_token_id,
|
203 |
+
eos_token_id=eos_token_id,
|
204 |
+
tie_word_embeddings=tie_word_embeddings,
|
205 |
+
**kwargs,
|
206 |
+
)
|
generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 100000,
|
4 |
+
"eos_token_id": 100001,
|
5 |
+
"do_sample": true,
|
6 |
+
"temperature": 0.3,
|
7 |
+
"top_p": 0.95,
|
8 |
+
"transformers_version": "4.39.3"
|
9 |
+
}
|
model-00001-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a00cc8c4f4a30ca3f51358f40c7feaf919cccd0ab361ddde80474edd09b16bf
|
3 |
+
size 8594017186
|
model-00002-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3518101685dfb59b3f3478299165d9c79f0a86cfda44496a669df559ff832bf
|
3 |
+
size 8604902394
|
model-00003-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3867564e5453b3cc2a87f840a397633367ccbf5ec02e4cbc4e7f86391bf37435
|
3 |
+
size 8604902394
|
model-00004-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ea471d0d706d40e012078fd336c3c63aa65fb539ab921d0fb7bb0b1fc694bd9
|
3 |
+
size 8604902402
|
model-00005-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5c3a14ba4bfcb110ce4069717d8888f0cb734ddcb7901688dbda1d19b261ef0
|
3 |
+
size 8590441833
|
model-00006-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e1eb87f65048f08cce30624f40b38953922d40830611c286a0e6ccd3e1ec4c9
|
3 |
+
size 8604902329
|
model-00007-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdf3279739528d812e26bac3a87edd85cf10dbc68794a68ef1ee8e2e11f48690
|
3 |
+
size 8604902352
|
model-00008-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:276e3c99da253a0ca396b6210c7f55a0a0f55f6f21cab94283876128a2d15733
|
3 |
+
size 8604902352
|
model-00009-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:796d1b3043d95e716ee53a93ec61b46ab1049bb0f2ac02f27a78829dcedb7a19
|
3 |
+
size 8604902538
|
model-00010-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee97d159da9e6607627fea9c0520df380a09e4b30628a786f643a1281aa15e17
|
3 |
+
size 8604902887
|
model-00011-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a295ee00a030a19fcc13977319c594151692230477aba0812e240c6c4640178b
|
3 |
+
size 8604902887
|
model-00012-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8479fe5936b2b518c0205e3876f58c7b51ebb6c33f3c61cab739df0e11a5ffe1
|
3 |
+
size 8604902888
|
model-00013-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f6a9aed13ce267712bb3de9900b459df895bdcbc57023621e0330ecdc363e70
|
3 |
+
size 8604902929
|
model-00014-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5058b6cf42548702e4eaa6fba600f352354e38800fc437903681f0acec38acce
|
3 |
+
size 8604902929
|
model-00015-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b540202c340ba05c2095a0d225d0d650a2d68e1bff85b5d7648ffaab51c9a36b
|
3 |
+
size 8604902929
|
model-00016-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f400f3746f531e7973ec938d7c8da28cc1aed18475ed8e6f94e2467a59f6c7ea
|
3 |
+
size 8604902933
|
model-00017-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9127ee9b304e5684074228b528135f62d0f370df900f6563f9d60c9620e48bf
|
3 |
+
size 8590442357
|
model-00018-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:000a774dd7129363c3735ad40f9170d8ca74941182cc91589a2486f63653f6ae
|
3 |
+
size 8604902862
|
model-00019-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80f4cb3b3acaceedb7ea8ef94db873da32b4e967459e46539961351d0c751633
|
3 |
+
size 8604902887
|
model-00020-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f2f4fab3be6be31cc0a61e18fdb610754bf5d4d8486c6ae0e7dc621c3983eea
|
3 |
+
size 8604902887
|
model-00021-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7445508daf1dae7309e57a1eb89b0473c88d86b5d76e1ba663a87ea118c0f6bb
|
3 |
+
size 8604902887
|
model-00022-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d313e5ef5e0123a7bdd353f3ba7f17335b94ea866a6f1deffdcaa5b0b5d0bec
|
3 |
+
size 8604902887
|
model-00023-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d061c215473dfd701de6fe45c31fa9fc62dae3948906b4aa2d7ad1a75d4e422e
|
3 |
+
size 8604902887
|
model-00024-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fe273f3a6d4fc44f773bfc3fcec741a3617a40cd7bb06bee12edb1941465e91
|
3 |
+
size 8604902887
|
model-00025-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02fff5dbcd7cfb382c704fba7ffdeb22ccbb4d59241b257fd8dafdf48e80d551
|
3 |
+
size 8604902928
|
model-00026-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0da8b7f7026baad7041dcfe237d80db0818ffb827b7b71fcf47bf5564b57b2ab
|
3 |
+
size 8604902929
|
model-00027-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a7332ded249b5ef38ec7db868985154b463e8e0734c4cab43d0e982be9f27c1
|
3 |
+
size 8604902929
|
model-00028-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbba8eaae706cfbabddc7d4fe2672c05d423aaa47d86202a6ace3a2aa11d65ce
|
3 |
+
size 8604902929
|
model-00029-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a203eda8699386ef27bf1470e8fbad84a082fd23257a9e64e82d1cdf81130049
|
3 |
+
size 8590442363
|
model-00030-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84a87c40dfaab1b4268a2da10437d5a2dab5d5c66f590f762d0b892085be1282
|
3 |
+
size 8604902860
|
model-00031-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42d3ccc93f8692e0876179ae60dfba74f3aa9d2a0e1db3f52ee5e11f2b561d85
|
3 |
+
size 8604902887
|
model-00032-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:848a8bcf39bbce5196f363adbe7a5b6502ac1f3947012d28a97a6fbd9dcd47ab
|
3 |
+
size 8604902887
|
model-00033-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d7691bb84b6717da267cec938329a7e688a2b148af8da85f5fddb9aebf4ef79
|
3 |
+
size 8604902887
|
model-00034-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58018261840fd8b6a10f1fd6bd972c1f997ac1578f6b1f3cc677698b7d0c0ff8
|
3 |
+
size 8604902887
|
model-00035-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66ae07756ca1b07fbbf358ec9143c0146244edb7429aec6a54386e78e985790a
|
3 |
+
size 8604902887
|
model-00036-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1326f23bb39fd6efcae3bcaf31c8bd914322503334709c96ed5962959fa9da9
|
3 |
+
size 8604902887
|
model-00037-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09f6d19e6e64cee713150f59956085cf8f031499ffcc5733581ee33e6386ebb2
|
3 |
+
size 8604902926
|
model-00038-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b2bc5527512937ce8c30914c329ba7431a51369a38d04d6e07f1498fb2acc55
|
3 |
+
size 8604902929
|
model-00039-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb999eeef7622b89b9eff6faf66cf67d6c190c578c18a8853c11dfe22c7c055b
|
3 |
+
size 8604902929
|
model-00040-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24151f39202225b6a55c98b9d46edcae7b08d5c1482b8089bd5d06dc1e54ed66
|
3 |
+
size 8604902927
|
model-00041-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e716ce3c0126e8e5786399d21279968c5878c2ac2e6befe49000636517873c5c
|
3 |
+
size 8590442367
|
model-00042-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4841b7da4767b1cb537e6eb69830709fc92dc4592e7ecf2a543986892a6b68c
|
3 |
+
size 8604902858
|
model-00043-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db9bd766abb0f6767aa502f654f90f695cc413677766d8e68c5c4bbc9b77fa6a
|
3 |
+
size 8604902887
|
model-00044-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e72e6993f5e9de148f962c4846a857b51e6362c611f2da5290e0b15019e34587
|
3 |
+
size 8604902887
|
model-00045-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da146da829f32b76db0fae376363a32925b74f3d38eb463b46eaf61115da5b10
|
3 |
+
size 8604902887
|
model-00046-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d1ddf539aa57ca468b92e3963a21ec61eff910661dfb18db4d65494364d2691
|
3 |
+
size 8604902887
|
model-00047-of-000055.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:770b443a270b871dbe06f64140fd7422b5a62186e20f1cbf5716babb3c9dd12c
|
3 |
+
size 8604902887
|