Hugging Face's logo

onnx-community
/
Phi-4-mini-instruct-web-q4f16

ONNX
phi3
Model card Files Community
1
Xenova HF staff commited on
Commit
d6eb3e0
·
verified ·
1 Parent(s): d4339cf

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. .gitattributes +3 -0
  2. added_tokens.json +12 -0
  3. config.json +152 -0
  4. generation_config.json +10 -0
  5. merges.txt +0 -0
  6. onnx/model_q4f16.onnx +3 -0
  7. onnx/model_q4f16.onnx_data +3 -0
  8. onnx/model_q4f16.onnx_data_1 +3 -0
  9. special_tokens_map.json +30 -0
  10. tokenizer.json +3 -0
  11. tokenizer_config.json +112 -0
  12. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,6 @@ 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
+ 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
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
+ }
config.json ADDED
@@ -0,0 +1,152 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/Phi-4-mini-instruct",
3
+ "architectures": [
4
+ "Phi3ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "microsoft/Phi-4-mini-instruct--configuration_phi3.Phi3Config",
10
+ "AutoModelForCausalLM": "microsoft/Phi-4-mini-instruct--modeling_phi3.Phi3ForCausalLM",
11
+ "AutoTokenizer": "microsoft/Phi-4-mini-instruct--Xenova/gpt-4o"
12
+ },
13
+ "bos_token_id": 199999,
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
+ "resid_pdrop": 0.0,
33
+ "rms_norm_eps": 1e-05,
34
+ "rope_scaling": {
35
+ "long_factor": [
36
+ 1,
37
+ 1.118320672,
38
+ 1.250641126,
39
+ 1.398617824,
40
+ 1.564103225,
41
+ 1.74916897,
42
+ 1.956131817,
43
+ 2.187582649,
44
+ 2.446418898,
45
+ 2.735880826,
46
+ 3.059592084,
47
+ 3.421605075,
48
+ 3.826451687,
49
+ 4.279200023,
50
+ 4.785517845,
51
+ 5.351743533,
52
+ 5.984965424,
53
+ 6.693110555,
54
+ 7.485043894,
55
+ 8.370679318,
56
+ 9.36110372,
57
+ 10.4687158,
58
+ 11.70738129,
59
+ 13.09260651,
60
+ 14.64173252,
61
+ 16.37415215,
62
+ 18.31155283,
63
+ 20.47818807,
64
+ 22.90118105,
65
+ 25.61086418,
66
+ 28.64115884,
67
+ 32.03,
68
+ 32.1,
69
+ 32.13,
70
+ 32.23,
71
+ 32.6,
72
+ 32.61,
73
+ 32.64,
74
+ 32.66,
75
+ 32.7,
76
+ 32.71,
77
+ 32.93,
78
+ 32.97,
79
+ 33.28,
80
+ 33.49,
81
+ 33.5,
82
+ 44.16,
83
+ 47.77
84
+ ],
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
+ "rope_theta": 10000.0,
138
+ "sliding_window": 262144,
139
+ "tie_word_embeddings": true,
140
+ "torch_dtype": "bfloat16",
141
+ "transformers_version": "4.50.0.dev0",
142
+ "use_cache": true,
143
+ "vocab_size": 200064,
144
+ "transformers.js_config": {
145
+ "dtype": "q4f16",
146
+ "kv_cache_dtype": {
147
+ "q4f16": "float16",
148
+ "fp16": "float16"
149
+ },
150
+ "use_external_data_format": 2
151
+ }
152
+ }
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": "4.50.0.dev0"
10
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
onnx/model_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c33161f7ec7d7e8921b77823185ec9c43ab63a105d63375673f1f579284572c6
3
+ size 291159
onnx/model_q4f16.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b383cab285b493c5e4e5eb27b343944873becdc6fe53a4a892fbc84617a024b
3
+ size 1993777152
onnx/model_q4f16.onnx_data_1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d087f38ea375599203a493fba54083c986eae10e8a66c694c6347b7969775aab
3
+ size 1419417600
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 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "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 %}",
105
+ "clean_up_tokenization_spaces": false,
106
+ "eos_token": "<|endoftext|>",
107
+ "extra_special_tokens": {},
108
+ "model_max_length": 131072,
109
+ "pad_token": "<|endoftext|>",
110
+ "tokenizer_class": "GPT2Tokenizer",
111
+ "unk_token": "<|endoftext|>"
112
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff