Hugging Face's logo

webgpu
/
Phi-4-mini-instruct-ONNX

ONNX
phi3
Model card Files
xet
 Community
captainspock commited on
Commit
74fe478
·
verified ·
1 Parent(s): 41b6396

Upload 7 files

Browse files
Files changed (8) hide show
  1. .gitattributes +1 -0
  2. README.md +4 -0
  3. chat_template.jinja +1 -0
  4. config.json +155 -0
  5. generation_config.json +10 -0
  6. gitattributes +55 -0
  7. tokenizer.json +3 -0
  8. tokenizer_config.json +13 -0
.gitattributes CHANGED
@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  onnx/model_q4f16.onnx_data filter=lfs diff=lfs merge=lfs -text
37
  onnx/model_q4f16.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
 
 
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  onnx/model_q4f16.onnx_data filter=lfs diff=lfs merge=lfs -text
37
  onnx/model_q4f16.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - microsoft/Phi-4-mini-instruct
4
+ ---
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 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Phi3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 199999,
8
+ "dtype": "bfloat16",
9
+ "embd_pdrop": 0.0,
10
+ "eos_token_id": 199999,
11
+ "full_attn_mod": 1,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 3072,
14
+ "ignore_keys_at_rope_validation": null,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 8192,
17
+ "interpolate_factor": 1,
18
+ "lm_head_bias": false,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "phi3",
22
+ "num_attention_heads": 24,
23
+ "num_hidden_layers": 32,
24
+ "num_key_value_heads": 8,
25
+ "original_max_position_embeddings": 4096,
26
+ "pad_token_id": 199999,
27
+ "partial_rotary_factor": 0.75,
28
+ "resid_pdrop": 0.0,
29
+ "rms_norm_eps": 1e-05,
30
+ "rope_parameters": {
31
+ "long_factor": [
32
+ 1,
33
+ 1.118320672,
34
+ 1.250641126,
35
+ 1.398617824,
36
+ 1.564103225,
37
+ 1.74916897,
38
+ 1.956131817,
39
+ 2.187582649,
40
+ 2.446418898,
41
+ 2.735880826,
42
+ 3.059592084,
43
+ 3.421605075,
44
+ 3.826451687,
45
+ 4.279200023,
46
+ 4.785517845,
47
+ 5.351743533,
48
+ 5.984965424,
49
+ 6.693110555,
50
+ 7.485043894,
51
+ 8.370679318,
52
+ 9.36110372,
53
+ 10.4687158,
54
+ 11.70738129,
55
+ 13.09260651,
56
+ 14.64173252,
57
+ 16.37415215,
58
+ 18.31155283,
59
+ 20.47818807,
60
+ 22.90118105,
61
+ 25.61086418,
62
+ 28.64115884,
63
+ 32.03,
64
+ 32.1,
65
+ 32.13,
66
+ 32.23,
67
+ 32.6,
68
+ 32.61,
69
+ 32.64,
70
+ 32.66,
71
+ 32.7,
72
+ 32.71,
73
+ 32.93,
74
+ 32.97,
75
+ 33.28,
76
+ 33.49,
77
+ 33.5,
78
+ 44.16,
79
+ 47.77
80
+ ],
81
+ "original_max_position_embeddings": 4096,
82
+ "partial_rotary_factor": 0.75,
83
+ "rope_theta": 10000.0,
84
+ "rope_type": "longrope",
85
+ "short_factor": [
86
+ 1.0,
87
+ 1.0,
88
+ 1.0,
89
+ 1.0,
90
+ 1.0,
91
+ 1.0,
92
+ 1.0,
93
+ 1.0,
94
+ 1.0,
95
+ 1.0,
96
+ 1.0,
97
+ 1.0,
98
+ 1.0,
99
+ 1.0,
100
+ 1.0,
101
+ 1.0,
102
+ 1.0,
103
+ 1.0,
104
+ 1.0,
105
+ 1.0,
106
+ 1.0,
107
+ 1.0,
108
+ 1.0,
109
+ 1.0,
110
+ 1.0,
111
+ 1.0,
112
+ 1.0,
113
+ 1.0,
114
+ 1.0,
115
+ 1.0,
116
+ 1.0,
117
+ 1.0,
118
+ 1.0,
119
+ 1.0,
120
+ 1.0,
121
+ 1.0,
122
+ 1.0,
123
+ 1.0,
124
+ 1.0,
125
+ 1.0,
126
+ 1.0,
127
+ 1.0,
128
+ 1.0,
129
+ 1.0,
130
+ 1.0,
131
+ 1.0,
132
+ 1.0,
133
+ 1.0
134
+ ],
135
+ "type": "longrope"
136
+ },
137
+ "sliding_window": 262144,
138
+ "tie_word_embeddings": true,
139
+ "transformers_version": "5.1.0",
140
+ "use_cache": true,
141
+ "vocab_size": 200064,
142
+ "transformers.js_config": {
143
+ "use_external_data_format": {
144
+ "model.onnx": 8,
145
+ "model_fp16.onnx": 4,
146
+ "model_quantized.onnx": 4,
147
+ "model_q4.onnx": 3,
148
+ "model_q4f16.onnx": 3
149
+ },
150
+ "kv_cache_dtype": {
151
+ "q4f16": "float16",
152
+ "fp16": "float16"
153
+ }
154
+ }
155
+ }
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": "5.1.0"
10
+ }
gitattributes ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz 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
+ onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text
37
+ onnx/model.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
38
+ onnx/model.onnx_data_2 filter=lfs diff=lfs merge=lfs -text
39
+ onnx/model.onnx_data_3 filter=lfs diff=lfs merge=lfs -text
40
+ onnx/model.onnx_data_4 filter=lfs diff=lfs merge=lfs -text
41
+ onnx/model.onnx_data_5 filter=lfs diff=lfs merge=lfs -text
42
+ onnx/model.onnx_data_6 filter=lfs diff=lfs merge=lfs -text
43
+ onnx/model.onnx_data_7 filter=lfs diff=lfs merge=lfs -text
44
+ onnx/model_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text
45
+ onnx/model_fp16.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
46
+ onnx/model_fp16.onnx_data_2 filter=lfs diff=lfs merge=lfs -text
47
+ onnx/model_fp16.onnx_data_3 filter=lfs diff=lfs merge=lfs -text
48
+ onnx/model_q4.onnx_data filter=lfs diff=lfs merge=lfs -text
49
+ onnx/model_q4.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
50
+ onnx/model_q4f16.onnx_data filter=lfs diff=lfs merge=lfs -text
51
+ onnx/model_q4f16.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
52
+ onnx/model_quantized.onnx_data filter=lfs diff=lfs merge=lfs -text
53
+ onnx/model_quantized.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
54
+ onnx/model_quantized.onnx_data_2 filter=lfs diff=lfs merge=lfs -text
55
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ca5aa723a31a7a122497e059bd48dd67a5bd03ad16b3ffcf16093fd3021c1eb
3
+ size 13303196
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|endoftext|>",
7
+ "is_local": false,
8
+ "model_max_length": 131072,
9
+ "pad_token": "<|endoftext|>",
10
+ "tokenizer_class": "TokenizersBackend",
11
+ "unk_token": "<|endoftext|>",
12
+ "chat_template": "{% 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 %}"
13
+ }