Hugging Face's logo

pytorch
/
Phi-4-mini-instruct-parq-3w-4e-shared

Text Generation
Transformers
PyTorch
multilingual
phi3
torchao
phi
phi4
nlp
code
math
chat
conversational
custom_code
text-generation-inference
Model card Files
xet
Community
2
lvj commited on
Commit
8acda3b
·
1 Parent(s): 77db1f5

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +12 -0
  3. chat_template.jinja +1 -0
  4. config.json +273 -0
  5. generation_config.json +10 -0
  6. merges.txt +0 -0
  7. special_tokens_map.json +30 -0
  8. tokenizer.json +3 -0
  9. tokenizer_config.json +111 -0
  10. training_args.bin +3 -0
  11. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|/tool_call|>": 200026,
3
+ "<|/tool|>": 200024,
4
+ "<|assistant|>": 200019,
5
+ "<|end|>": 200020,
6
+ "<|system|>": 200022,
7
+ "<|tag|>": 200028,
8
+ "<|tool_call|>": 200025,
9
+ "<|tool_response|>": 200027,
10
+ "<|tool|>": 200023,
11
+ "<|user|>": 200021
12
+ }
chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}
config.json ADDED
@@ -0,0 +1,273 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Phi3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_phi3.Phi3Config",
9
+ "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM",
10
+ "AutoTokenizer": "Xenova/gpt-4o"
11
+ },
12
+ "bos_token_id": 199999,
13
+ "dtype": "bfloat16",
14
+ "embd_pdrop": 0.0,
15
+ "eos_token_id": 199999,
16
+ "full_attn_mod": 1,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 3072,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 8192,
21
+ "interpolate_factor": 1,
22
+ "lm_head_bias": false,
23
+ "max_position_embeddings": 131072,
24
+ "mlp_bias": false,
25
+ "model_type": "phi3",
26
+ "num_attention_heads": 24,
27
+ "num_hidden_layers": 32,
28
+ "num_key_value_heads": 8,
29
+ "original_max_position_embeddings": 4096,
30
+ "pad_token_id": 199999,
31
+ "partial_rotary_factor": 0.75,
32
+ "quantization_config": {
33
+ "include_input_output_embeddings": true,
34
+ "modules_to_not_convert": [
35
+ "model.layers.0.input_layernorm",
36
+ "model.layers.0.post_attention_layernorm",
37
+ "model.layers.1.input_layernorm",
38
+ "model.layers.1.post_attention_layernorm",
39
+ "model.layers.2.input_layernorm",
40
+ "model.layers.2.post_attention_layernorm",
41
+ "model.layers.3.input_layernorm",
42
+ "model.layers.3.post_attention_layernorm",
43
+ "model.layers.4.input_layernorm",
44
+ "model.layers.4.post_attention_layernorm",
45
+ "model.layers.5.input_layernorm",
46
+ "model.layers.5.post_attention_layernorm",
47
+ "model.layers.6.input_layernorm",
48
+ "model.layers.6.post_attention_layernorm",
49
+ "model.layers.7.input_layernorm",
50
+ "model.layers.7.post_attention_layernorm",
51
+ "model.layers.8.input_layernorm",
52
+ "model.layers.8.post_attention_layernorm",
53
+ "model.layers.9.input_layernorm",
54
+ "model.layers.9.post_attention_layernorm",
55
+ "model.layers.10.input_layernorm",
56
+ "model.layers.10.post_attention_layernorm",
57
+ "model.layers.11.input_layernorm",
58
+ "model.layers.11.post_attention_layernorm",
59
+ "model.layers.12.input_layernorm",
60
+ "model.layers.12.post_attention_layernorm",
61
+ "model.layers.13.input_layernorm",
62
+ "model.layers.13.post_attention_layernorm",
63
+ "model.layers.14.input_layernorm",
64
+ "model.layers.14.post_attention_layernorm",
65
+ "model.layers.15.input_layernorm",
66
+ "model.layers.15.post_attention_layernorm",
67
+ "model.layers.16.input_layernorm",
68
+ "model.layers.16.post_attention_layernorm",
69
+ "model.layers.17.input_layernorm",
70
+ "model.layers.17.post_attention_layernorm",
71
+ "model.layers.18.input_layernorm",
72
+ "model.layers.18.post_attention_layernorm",
73
+ "model.layers.19.input_layernorm",
74
+ "model.layers.19.post_attention_layernorm",
75
+ "model.layers.20.input_layernorm",
76
+ "model.layers.20.post_attention_layernorm",
77
+ "model.layers.21.input_layernorm",
78
+ "model.layers.21.post_attention_layernorm",
79
+ "model.layers.22.input_layernorm",
80
+ "model.layers.22.post_attention_layernorm",
81
+ "model.layers.23.input_layernorm",
82
+ "model.layers.23.post_attention_layernorm",
83
+ "model.layers.24.input_layernorm",
84
+ "model.layers.24.post_attention_layernorm",
85
+ "model.layers.25.input_layernorm",
86
+ "model.layers.25.post_attention_layernorm",
87
+ "model.layers.26.input_layernorm",
88
+ "model.layers.26.post_attention_layernorm",
89
+ "model.layers.27.input_layernorm",
90
+ "model.layers.27.post_attention_layernorm",
91
+ "model.layers.28.input_layernorm",
92
+ "model.layers.28.post_attention_layernorm",
93
+ "model.layers.29.input_layernorm",
94
+ "model.layers.29.post_attention_layernorm",
95
+ "model.layers.30.input_layernorm",
96
+ "model.layers.30.post_attention_layernorm",
97
+ "model.layers.31.input_layernorm",
98
+ "model.layers.31.post_attention_layernorm",
99
+ "model.norm",
100
+ "lm_head"
101
+ ],
102
+ "quant_method": "torchao",
103
+ "quant_type": {
104
+ "default": {
105
+ "_data": {
106
+ "module_fqn_to_config": {
107
+ "_default": {
108
+ "_data": {
109
+ "activation_quantization": "int8_asym_per_token",
110
+ "b": 3,
111
+ "granularity": {
112
+ "_data": {
113
+ "axis": 0
114
+ },
115
+ "_type": "PerAxis",
116
+ "_version": 1
117
+ },
118
+ "layout": {
119
+ "_data": {},
120
+ "_type": "QDQLayout",
121
+ "_version": 1
122
+ },
123
+ "quant_max": 3.5,
124
+ "quant_min": -3.5,
125
+ "scale_dtype": null
126
+ },
127
+ "_type": "StretchedIntxWeightConfig",
128
+ "_version": 2
129
+ },
130
+ "model.embed_tokens": {
131
+ "_data": {
132
+ "activation_quantization": "int8_asym_per_token",
133
+ "b": 3,
134
+ "granularity": {
135
+ "_data": {
136
+ "axis": 0
137
+ },
138
+ "_type": "PerAxis",
139
+ "_version": 1
140
+ },
141
+ "layout": {
142
+ "_data": {},
143
+ "_type": "QDQLayout",
144
+ "_version": 1
145
+ },
146
+ "quant_max": 3.5,
147
+ "quant_min": -3.5,
148
+ "scale_dtype": null
149
+ },
150
+ "_type": "StretchedIntxWeightConfig",
151
+ "_version": 2
152
+ }
153
+ }
154
+ },
155
+ "_type": "ModuleFqnToConfig",
156
+ "_version": 1
157
+ }
158
+ },
159
+ "quant_type_kwargs": {},
160
+ "untie_embedding_weights": false
161
+ },
162
+ "resid_pdrop": 0.0,
163
+ "rms_norm_eps": 1e-05,
164
+ "rope_scaling": {
165
+ "long_factor": [
166
+ 1,
167
+ 1.118320672,
168
+ 1.250641126,
169
+ 1.398617824,
170
+ 1.564103225,
171
+ 1.74916897,
172
+ 1.956131817,
173
+ 2.187582649,
174
+ 2.446418898,
175
+ 2.735880826,
176
+ 3.059592084,
177
+ 3.421605075,
178
+ 3.826451687,
179
+ 4.279200023,
180
+ 4.785517845,
181
+ 5.351743533,
182
+ 5.984965424,
183
+ 6.693110555,
184
+ 7.485043894,
185
+ 8.370679318,
186
+ 9.36110372,
187
+ 10.4687158,
188
+ 11.70738129,
189
+ 13.09260651,
190
+ 14.64173252,
191
+ 16.37415215,
192
+ 18.31155283,
193
+ 20.47818807,
194
+ 22.90118105,
195
+ 25.61086418,
196
+ 28.64115884,
197
+ 32.03,
198
+ 32.1,
199
+ 32.13,
200
+ 32.23,
201
+ 32.6,
202
+ 32.61,
203
+ 32.64,
204
+ 32.66,
205
+ 32.7,
206
+ 32.71,
207
+ 32.93,
208
+ 32.97,
209
+ 33.28,
210
+ 33.49,
211
+ 33.5,
212
+ 44.16,
213
+ 47.77
214
+ ],
215
+ "short_factor": [
216
+ 1.0,
217
+ 1.0,
218
+ 1.0,
219
+ 1.0,
220
+ 1.0,
221
+ 1.0,
222
+ 1.0,
223
+ 1.0,
224
+ 1.0,
225
+ 1.0,
226
+ 1.0,
227
+ 1.0,
228
+ 1.0,
229
+ 1.0,
230
+ 1.0,
231
+ 1.0,
232
+ 1.0,
233
+ 1.0,
234
+ 1.0,
235
+ 1.0,
236
+ 1.0,
237
+ 1.0,
238
+ 1.0,
239
+ 1.0,
240
+ 1.0,
241
+ 1.0,
242
+ 1.0,
243
+ 1.0,
244
+ 1.0,
245
+ 1.0,
246
+ 1.0,
247
+ 1.0,
248
+ 1.0,
249
+ 1.0,
250
+ 1.0,
251
+ 1.0,
252
+ 1.0,
253
+ 1.0,
254
+ 1.0,
255
+ 1.0,
256
+ 1.0,
257
+ 1.0,
258
+ 1.0,
259
+ 1.0,
260
+ 1.0,
261
+ 1.0,
262
+ 1.0,
263
+ 1.0
264
+ ],
265
+ "type": "longrope"
266
+ },
267
+ "rope_theta": 10000.0,
268
+ "sliding_window": 262144,
269
+ "tie_word_embeddings": true,
270
+ "transformers_version": "4.56.2",
271
+ "use_cache": true,
272
+ "vocab_size": 200064
273
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 199999,
4
+ "eos_token_id": [
5
+ 200020,
6
+ 199999
7
+ ],
8
+ "pad_token_id": 199999,
9
+ "transformers_version": "4.56.2"
10
+ }
merges.txt 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": "<|endoftext|>",
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": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:382cc235b56c725945e149cc25f191da667c836655efd0857b004320e90e91ea
3
+ size 15524095
tokenizer_config.json ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "199999": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "200018": {
15
+ "content": "<|endofprompt|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "200019": {
23
+ "content": "<|assistant|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "200020": {
31
+ "content": "<|end|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": true,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "200021": {
39
+ "content": "<|user|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "200022": {
47
+ "content": "<|system|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "200023": {
55
+ "content": "<|tool|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "200024": {
63
+ "content": "<|/tool|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "200025": {
71
+ "content": "<|tool_call|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "200026": {
79
+ "content": "<|/tool_call|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "200027": {
87
+ "content": "<|tool_response|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "200028": {
95
+ "content": "<|tag|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ }
102
+ },
103
+ "bos_token": "<|endoftext|>",
104
+ "clean_up_tokenization_spaces": false,
105
+ "eos_token": "<|endoftext|>",
106
+ "extra_special_tokens": {},
107
+ "model_max_length": 131072,
108
+ "pad_token": "<|endoftext|>",
109
+ "tokenizer_class": "GPT2Tokenizer",
110
+ "unk_token": "<|endoftext|>"
111
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e487d7040897972de4c2033bac746c1cd004fabea9b8c1ac2f907abc7b537fd8
3
+ size 6417
vocab.json ADDED
The diff for this file is too large to render. See raw diff