Hugging Face's logo

m-muraki
/
Phi-4-mini-reasoning-FP8-Dynamic

Safetensors
phi3
compressed-tensors
Model card Files
xet
 Community
m-muraki commited on
Commit
772aae1
·
verified ·
1 Parent(s): dc757a4

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +12 -0
  3. chat_template.jinja +1 -0
  4. config.json +180 -0
  5. generation_config.json +10 -0
  6. merges.txt +0 -0
  7. model.safetensors +3 -0
  8. recipe.yaml +6 -0
  9. special_tokens_map.json +30 -0
  10. tokenizer.json +3 -0
  11. tokenizer_config.json +115 -0
  12. 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
+ {{ '<|system|>Your name is Phi, an AI math expert developed by Microsoft.' }}{% for message in messages %}{% if message['role'] == 'system' %} {{ message['content'] }}{% if 'tools' in message and message['tools'] is not none %}{{ '<|tool|>' + message['tools'] + '<|/tool|>' }}{% endif %}{% endif %}{% endfor %}{{ '<|end|>' }}{% for message in messages %}{% if message['role'] != 'system' %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}
config.json ADDED
@@ -0,0 +1,180 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Phi3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 199999,
8
+ "embd_pdrop": 0.0,
9
+ "eos_token_id": 199999,
10
+ "full_attn_mod": 1,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 3072,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 8192,
15
+ "interpolate_factor": 1,
16
+ "lm_head_bias": false,
17
+ "max_position_embeddings": 131072,
18
+ "mlp_bias": false,
19
+ "model_type": "phi3",
20
+ "num_attention_heads": 24,
21
+ "num_hidden_layers": 32,
22
+ "num_key_value_heads": 8,
23
+ "original_max_position_embeddings": 4096,
24
+ "pad_token_id": 199999,
25
+ "partial_rotary_factor": 0.75,
26
+ "quantization_config": {
27
+ "config_groups": {
28
+ "group_0": {
29
+ "input_activations": {
30
+ "actorder": null,
31
+ "block_structure": null,
32
+ "dynamic": true,
33
+ "group_size": null,
34
+ "num_bits": 8,
35
+ "observer": null,
36
+ "observer_kwargs": {},
37
+ "strategy": "token",
38
+ "symmetric": true,
39
+ "type": "float"
40
+ },
41
+ "output_activations": null,
42
+ "targets": [
43
+ "Linear"
44
+ ],
45
+ "weights": {
46
+ "actorder": null,
47
+ "block_structure": null,
48
+ "dynamic": false,
49
+ "group_size": null,
50
+ "num_bits": 8,
51
+ "observer": "minmax",
52
+ "observer_kwargs": {},
53
+ "strategy": "channel",
54
+ "symmetric": true,
55
+ "type": "float"
56
+ }
57
+ }
58
+ },
59
+ "format": "float-quantized",
60
+ "global_compression_ratio": null,
61
+ "ignore": [
62
+ "lm_head"
63
+ ],
64
+ "kv_cache_scheme": null,
65
+ "quant_method": "compressed-tensors",
66
+ "quantization_status": "compressed"
67
+ },
68
+ "resid_pdrop": 0.0,
69
+ "rms_norm_eps": 1e-05,
70
+ "rope_scaling": {
71
+ "long_factor": [
72
+ 1,
73
+ 1.118320672,
74
+ 1.250641126,
75
+ 1.398617824,
76
+ 1.564103225,
77
+ 1.74916897,
78
+ 1.956131817,
79
+ 2.187582649,
80
+ 2.446418898,
81
+ 2.735880826,
82
+ 3.059592084,
83
+ 3.421605075,
84
+ 3.826451687,
85
+ 4.279200023,
86
+ 4.785517845,
87
+ 5.351743533,
88
+ 5.984965424,
89
+ 6.693110555,
90
+ 7.485043894,
91
+ 8.370679318,
92
+ 9.36110372,
93
+ 10.4687158,
94
+ 11.70738129,
95
+ 13.09260651,
96
+ 14.64173252,
97
+ 16.37415215,
98
+ 18.31155283,
99
+ 20.47818807,
100
+ 22.90118105,
101
+ 25.61086418,
102
+ 28.64115884,
103
+ 32.03,
104
+ 32.1,
105
+ 32.13,
106
+ 32.23,
107
+ 32.6,
108
+ 32.61,
109
+ 32.64,
110
+ 32.66,
111
+ 32.7,
112
+ 32.71,
113
+ 32.93,
114
+ 32.97,
115
+ 33.28,
116
+ 33.49,
117
+ 33.5,
118
+ 44.16,
119
+ 47.77
120
+ ],
121
+ "short_factor": [
122
+ 1,
123
+ 1.118320672,
124
+ 1.250641126,
125
+ 1.398617824,
126
+ 1.564103225,
127
+ 1.74916897,
128
+ 1.956131817,
129
+ 2.187582649,
130
+ 2.446418898,
131
+ 2.735880826,
132
+ 3.059592084,
133
+ 3.421605075,
134
+ 3.826451687,
135
+ 4.279200023,
136
+ 4.785517845,
137
+ 5.351743533,
138
+ 5.984965424,
139
+ 6.693110555,
140
+ 7.485043894,
141
+ 8.370679318,
142
+ 9.36110372,
143
+ 10.4687158,
144
+ 11.70738129,
145
+ 13.09260651,
146
+ 14.64173252,
147
+ 16.37415215,
148
+ 18.31155283,
149
+ 20.47818807,
150
+ 22.90118105,
151
+ 25.61086418,
152
+ 28.64115884,
153
+ 32.03,
154
+ 32.1,
155
+ 32.13,
156
+ 32.23,
157
+ 32.6,
158
+ 32.61,
159
+ 32.64,
160
+ 32.66,
161
+ 32.7,
162
+ 32.71,
163
+ 32.93,
164
+ 32.97,
165
+ 33.28,
166
+ 33.49,
167
+ 33.5,
168
+ 44.16,
169
+ 47.77
170
+ ],
171
+ "type": "longrope"
172
+ },
173
+ "rope_theta": 10000.0,
174
+ "sliding_window": 262144,
175
+ "tie_word_embeddings": true,
176
+ "torch_dtype": "bfloat16",
177
+ "transformers_version": "4.52.4",
178
+ "use_cache": true,
179
+ "vocab_size": 200064
180
+ }
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": "4.52.4"
10
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adb1a8f19361d61e14743dcaee7bf9bc5327dee4280094c6f85f17228ad293d6
3
+ size 4452626080
recipe.yaml ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ default_stage:
2
+ default_modifiers:
3
+ QuantizationModifier:
4
+ ignore: [lm_head]
5
+ targets: [Linear]
6
+ scheme: FP8_DYNAMIC
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:f08ed885956f70d877a4d9078ec9e3119d8b68a8d579003e230be18cad66911c
3
+ size 15524194
tokenizer_config.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "max_length": 1024,
108
+ "model_max_length": 131072,
109
+ "pad_token": "<|endoftext|>",
110
+ "stride": 0,
111
+ "tokenizer_class": "GPT2Tokenizer",
112
+ "truncation_side": "right",
113
+ "truncation_strategy": "longest_first",
114
+ "unk_token": "<|endoftext|>"
115
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff