Hugging Face's logo

1024m
/
Phi-3.5-MoE-4bit-nf4

Safetensors
phimoe
custom_code
4-bit precision
bitsandbytes
Model card Files Community
1024m commited on
Commit
0e699ee
•
1 Parent(s): 63fb339

Upload folder using huggingface_hub

Browse files
Files changed (13) hide show
  1. added_tokens.json +13 -0
  2. config.json +193 -0
  3. generation_config.json +11 -0
  4. model-00001-of-00005.safetensors +3 -0
  5. model-00002-of-00005.safetensors +3 -0
  6. model-00003-of-00005.safetensors +3 -0
  7. model-00004-of-00005.safetensors +3 -0
  8. model-00005-of-00005.safetensors +3 -0
  9. model.safetensors.index.json +0 -0
  10. special_tokens_map.json +30 -0
  11. tokenizer.json +0 -0
  12. tokenizer.model +3 -0
  13. tokenizer_config.json +131 -0
added_tokens.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|assistant|>": 32001,
3
+ "<|endoftext|>": 32000,
4
+ "<|end|>": 32007,
5
+ "<|placeholder1|>": 32002,
6
+ "<|placeholder2|>": 32003,
7
+ "<|placeholder3|>": 32004,
8
+ "<|placeholder4|>": 32005,
9
+ "<|placeholder5|>": 32008,
10
+ "<|placeholder6|>": 32009,
11
+ "<|system|>": 32006,
12
+ "<|user|>": 32010
13
+ }
config.json ADDED
@@ -0,0 +1,193 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/Phi-3.5-MoE-instruct",
3
+ "architectures": [
4
+ "PhiMoEForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "microsoft/Phi-3.5-MoE-instruct--configuration_phimoe.PhiMoEConfig",
10
+ "AutoModelForCausalLM": "microsoft/Phi-3.5-MoE-instruct--modeling_phimoe.PhiMoEForCausalLM"
11
+ },
12
+ "bos_token_id": 1,
13
+ "eos_token_id": 32000,
14
+ "hidden_act": "silu",
15
+ "hidden_dropout": 0.0,
16
+ "hidden_size": 4096,
17
+ "initializer_range": 0.02,
18
+ "input_jitter_noise": 0.01,
19
+ "intermediate_size": 6400,
20
+ "lm_head_bias": true,
21
+ "max_position_embeddings": 131072,
22
+ "model_type": "phimoe",
23
+ "num_attention_heads": 32,
24
+ "num_experts_per_tok": 2,
25
+ "num_hidden_layers": 32,
26
+ "num_key_value_heads": 8,
27
+ "num_local_experts": 16,
28
+ "original_max_position_embeddings": 4096,
29
+ "output_router_logits": false,
30
+ "quantization_config": {
31
+ "_load_in_4bit": true,
32
+ "_load_in_8bit": false,
33
+ "bnb_4bit_compute_dtype": "bfloat16",
34
+ "bnb_4bit_quant_storage": "uint8",
35
+ "bnb_4bit_quant_type": "nf4",
36
+ "bnb_4bit_use_double_quant": true,
37
+ "llm_int8_enable_fp32_cpu_offload": false,
38
+ "llm_int8_has_fp16_weight": false,
39
+ "llm_int8_skip_modules": null,
40
+ "llm_int8_threshold": 6.0,
41
+ "load_in_4bit": true,
42
+ "load_in_8bit": false,
43
+ "quant_method": "bitsandbytes"
44
+ },
45
+ "rms_norm_eps": 1e-05,
46
+ "rope_scaling": {
47
+ "long_factor": [
48
+ 1.0199999809265137,
49
+ 1.0299999713897705,
50
+ 1.0399999618530273,
51
+ 1.0499999523162842,
52
+ 1.0499999523162842,
53
+ 1.0499999523162842,
54
+ 1.059999942779541,
55
+ 1.059999942779541,
56
+ 1.059999942779541,
57
+ 1.059999942779541,
58
+ 1.059999942779541,
59
+ 1.059999942779541,
60
+ 1.0999999046325684,
61
+ 1.1799999475479126,
62
+ 1.1799999475479126,
63
+ 1.3700000047683716,
64
+ 1.4899998903274536,
65
+ 2.109999895095825,
66
+ 2.8899998664855957,
67
+ 3.9499998092651367,
68
+ 4.299999713897705,
69
+ 6.429999828338623,
70
+ 8.09000015258789,
71
+ 10.690000534057617,
72
+ 12.050000190734863,
73
+ 18.229999542236328,
74
+ 18.84000015258789,
75
+ 19.899999618530273,
76
+ 21.420000076293945,
77
+ 26.200000762939453,
78
+ 34.28000259399414,
79
+ 34.590003967285156,
80
+ 38.730003356933594,
81
+ 40.22000503540039,
82
+ 42.54000473022461,
83
+ 44.000003814697266,
84
+ 47.590003967285156,
85
+ 54.750003814697266,
86
+ 56.19000244140625,
87
+ 57.44000244140625,
88
+ 57.4900016784668,
89
+ 61.20000076293945,
90
+ 61.540000915527344,
91
+ 61.75,
92
+ 61.779998779296875,
93
+ 62.06999969482422,
94
+ 63.11000061035156,
95
+ 63.43000030517578,
96
+ 63.560001373291016,
97
+ 63.71000289916992,
98
+ 63.92000198364258,
99
+ 63.94000244140625,
100
+ 63.94000244140625,
101
+ 63.96000289916992,
102
+ 63.980003356933594,
103
+ 64.0300064086914,
104
+ 64.0300064086914,
105
+ 64.0300064086914,
106
+ 64.04000854492188,
107
+ 64.10000610351562,
108
+ 64.19000244140625,
109
+ 64.20999908447266,
110
+ 64.75,
111
+ 64.95999908447266
112
+ ],
113
+ "long_mscale": 1.243163121016122,
114
+ "original_max_position_embeddings": 4096,
115
+ "short_factor": [
116
+ 1.0,
117
+ 1.0399999618530273,
118
+ 1.0399999618530273,
119
+ 1.0399999618530273,
120
+ 1.0499999523162842,
121
+ 1.0499999523162842,
122
+ 1.0499999523162842,
123
+ 1.0499999523162842,
124
+ 1.0499999523162842,
125
+ 1.0499999523162842,
126
+ 1.0499999523162842,
127
+ 1.0499999523162842,
128
+ 1.0499999523162842,
129
+ 1.0499999523162842,
130
+ 1.059999942779541,
131
+ 1.059999942779541,
132
+ 1.0699999332427979,
133
+ 1.0699999332427979,
134
+ 1.0699999332427979,
135
+ 1.0699999332427979,
136
+ 1.1399999856948853,
137
+ 1.159999966621399,
138
+ 1.159999966621399,
139
+ 1.159999966621399,
140
+ 1.159999966621399,
141
+ 1.1799999475479126,
142
+ 1.1999999284744263,
143
+ 1.3199999332427979,
144
+ 1.3399999141693115,
145
+ 1.3499999046325684,
146
+ 1.3999998569488525,
147
+ 1.4799998998641968,
148
+ 1.4999998807907104,
149
+ 1.589999794960022,
150
+ 1.6499998569488525,
151
+ 1.71999990940094,
152
+ 1.8999998569488525,
153
+ 1.9099998474121094,
154
+ 1.9099998474121094,
155
+ 1.9899998903274536,
156
+ 1.9999998807907104,
157
+ 1.9999998807907104,
158
+ 2.009999990463257,
159
+ 2.009999990463257,
160
+ 2.009999990463257,
161
+ 2.009999990463257,
162
+ 2.009999990463257,
163
+ 2.009999990463257,
164
+ 2.009999990463257,
165
+ 2.009999990463257,
166
+ 2.009999990463257,
167
+ 2.009999990463257,
168
+ 2.009999990463257,
169
+ 2.009999990463257,
170
+ 2.009999990463257,
171
+ 2.009999990463257,
172
+ 2.009999990463257,
173
+ 2.009999990463257,
174
+ 2.009999990463257,
175
+ 2.0999999046325684,
176
+ 2.319999933242798,
177
+ 2.419999837875366,
178
+ 2.5899999141693115,
179
+ 2.7899999618530273
180
+ ],
181
+ "short_mscale": 1.243163121016122,
182
+ "type": "longrope"
183
+ },
184
+ "rope_theta": 10000.0,
185
+ "router_aux_loss_coef": 0.0,
186
+ "router_jitter_noise": 0.01,
187
+ "sliding_window": 131072,
188
+ "tie_word_embeddings": false,
189
+ "torch_dtype": "float16",
190
+ "transformers_version": "4.42.4",
191
+ "use_cache": true,
192
+ "vocab_size": 32064
193
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 32000,
6
+ 32001,
7
+ 32007
8
+ ],
9
+ "pad_token_id": 32000,
10
+ "transformers_version": "4.42.4"
11
+ }
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1e1a088837c0c194f6a09d4f532e0fc09f5addf1ac2e675d634ea63f3ff522f
3
+ size 4994528724
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:383fbea5a0ef43165ebc3637b851dee64110873f695435d9d62b20604d1cf7e2
3
+ size 4994190164
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09d0bdef67ceed436d156a72cd42bace62787ef516e75b69b64a77956ad4eed6
3
+ size 4994191219
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51c9bc3037dc05276d11a604b6f34b5b0856055d70b92ad0f3ca4d066cd1b38c
3
+ size 4988875584
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e23f6869ede1f95dae9cad2e15cb8d049206a65e6cab3123807da4a46a1e8b45
3
+ size 2023960872
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|placeholder1|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|placeholder2|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|placeholder3|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|placeholder4|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|placeholder5|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|placeholder6|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ }
118
+ },
119
+ "bos_token": "<s>",
120
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|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 %}",
121
+ "clean_up_tokenization_spaces": false,
122
+ "eos_token": "<|endoftext|>",
123
+ "legacy": false,
124
+ "model_max_length": 131072,
125
+ "pad_token": "<|endoftext|>",
126
+ "padding_side": "left",
127
+ "sp_model_kwargs": {},
128
+ "tokenizer_class": "LlamaTokenizer",
129
+ "unk_token": "<unk>",
130
+ "use_default_system_prompt": false
131
+ }