Xenova HF Staff commited on
Commit
2cedd3f
·
verified ·
1 Parent(s): 9413299

Upload optimized ONNX model

Browse files
.gitattributes CHANGED
@@ -41,3 +41,13 @@ onnx/model_q4.onnx_data filter=lfs diff=lfs merge=lfs -text
41
  onnx/model_q4.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
42
  onnx/model_q4.onnx_data_2 filter=lfs diff=lfs merge=lfs -text
43
  onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
41
  onnx/model_q4.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
42
  onnx/model_q4.onnx_data_2 filter=lfs diff=lfs merge=lfs -text
43
  onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text
44
+ onnx/model.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
45
+ onnx/model.onnx_data_2 filter=lfs diff=lfs merge=lfs -text
46
+ onnx/model.onnx_data_3 filter=lfs diff=lfs merge=lfs -text
47
+ onnx/model.onnx_data_4 filter=lfs diff=lfs merge=lfs -text
48
+ onnx/model.onnx_data_5 filter=lfs diff=lfs merge=lfs -text
49
+ onnx/model.onnx_data_6 filter=lfs diff=lfs merge=lfs -text
50
+ onnx/model.onnx_data_7 filter=lfs diff=lfs merge=lfs -text
51
+ onnx/model_fp16.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
52
+ onnx/model_fp16.onnx_data_2 filter=lfs diff=lfs merge=lfs -text
53
+ onnx/model_fp16.onnx_data_3 filter=lfs diff=lfs merge=lfs -text
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 CHANGED
@@ -1,11 +1,16 @@
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
  "bos_token_id": 199999,
 
9
  "embd_pdrop": 0.0,
10
  "eos_token_id": 199999,
11
  "full_attn_mod": 1,
@@ -26,7 +31,7 @@
26
  "partial_rotary_factor": 0.75,
27
  "resid_pdrop": 0.0,
28
  "rms_norm_eps": 1e-05,
29
- "rope_scaling": {
30
  "long_factor": [
31
  1,
32
  1.118320672,
@@ -77,6 +82,8 @@
77
  44.16,
78
  47.77
79
  ],
 
 
80
  "short_factor": [
81
  1.0,
82
  1.0,
@@ -132,21 +139,19 @@
132
  "rope_theta": 10000.0,
133
  "sliding_window": 262144,
134
  "tie_word_embeddings": true,
135
- "torch_dtype": "bfloat16",
136
- "transformers_version": "4.50.0.dev0",
 
137
  "transformers.js_config": {
138
- "dtype": "q4f16",
 
 
 
 
 
139
  "kv_cache_dtype": {
140
  "q4f16": "float16",
141
  "fp16": "float16"
142
- },
143
- "use_external_data_format": {
144
- "model.onnx": 1,
145
- "model_fp16.onnx": 1,
146
- "model_q4.onnx": 3,
147
- "model_q4f16.onnx": 2
148
  }
149
- },
150
- "use_cache": true,
151
- "vocab_size": 200064
152
- }
 
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,
 
31
  "partial_rotary_factor": 0.75,
32
  "resid_pdrop": 0.0,
33
  "rms_norm_eps": 1e-05,
34
+ "rope_parameters": {
35
  "long_factor": [
36
  1,
37
  1.118320672,
 
82
  44.16,
83
  47.77
84
  ],
85
+ "rope_theta": 10000.0,
86
+ "rope_type": "longrope",
87
  "short_factor": [
88
  1.0,
89
  1.0,
 
139
  "rope_theta": 10000.0,
140
  "sliding_window": 262144,
141
  "tie_word_embeddings": true,
142
+ "transformers_version": "5.0.0.dev0",
143
+ "use_cache": true,
144
+ "vocab_size": 200064,
145
  "transformers.js_config": {
146
+ "use_external_data_format": {
147
+ "model.onnx": 8,
148
+ "model_fp16.onnx": 4,
149
+ "model_q4.onnx": 2,
150
+ "model_q4f16.onnx": 2
151
+ },
152
  "kv_cache_dtype": {
153
  "q4f16": "float16",
154
  "fp16": "float16"
 
 
 
 
 
 
155
  }
156
+ }
157
+ }
 
 
generation_config.json CHANGED
@@ -6,5 +6,5 @@
6
  199999
7
  ],
8
  "pad_token_id": 199999,
9
- "transformers_version": "4.50.0.dev0"
10
  }
 
6
  199999
7
  ],
8
  "pad_token_id": 199999,
9
+ "transformers_version": "5.0.0.dev0"
10
  }
onnx/model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99f68fa98585d95994b63d00f52f6cc4b2d72800a28e5daf3b2e3324d3cfae1a
3
- size 52127451
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d546a92ae6c422c0388e99bda1f6928f9d8ca3c5a536bb65a9352c83313df1b2
3
+ size 214405
onnx/model.onnx_data CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:544ee2b3b7235f10bf8ab4cc503361506229da0a89fd5699b548a7211261d123
3
- size 15344087040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5e003644ccf8a555bc8a47fb5f1db44be661c75495e6113af1e894afe2642c7
3
+ size 2458386432
onnx/model.onnx_data_1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8aae6a27a25e9f006d8d64b0b477fa71f395ea47e2410b7a6fb5a1557b3390a9
3
+ size 2076315648
onnx/model.onnx_data_2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8feb1b1b4f466b7e62e4bdfc3497568eb0df2a80ccbedcaf370ff2ef7a1d5704
3
+ size 2051149824
onnx/model.onnx_data_3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:203d8f6977f3566a56921a2b76bc6fece27f8d0548de94832bb57bd2da8bfa94
3
+ size 2013388800
onnx/model.onnx_data_4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fb8230de4ed19e78defb04432975fbb2ad4ef4f92cb54bbcacffc4e1e59f6bc
3
+ size 2013388800
onnx/model.onnx_data_5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:713e09c1343cc1e64a3f3fc157693ec3b08b353a0e89f0ae568bacaf7f0b3db1
3
+ size 2013388800
onnx/model.onnx_data_6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18330921aaf83d05e48130e67002b3ec7a122e17978721cbcabd62374603f800
3
+ size 2013388800
onnx/model.onnx_data_7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc52557ecf95f564fdf537a75de8d95852443261a6e4d747d69ca80401ec6541
3
+ size 756584448
onnx/model_fp16.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90fe357dac89134b3aa1cbfd83c20864ff7e26f4da7c5774799e9f1ce0174707
3
- size 224606
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc0deec8a535eb7ce9636f284457e77a2c58855b025314be3b80e2ac7a196457
3
+ size 215952
onnx/model_fp16.onnx_data CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d41fc13815d4a0da358e6d1abf8f50c15764255b364a095203bde2c58aa07e0d
3
- size 7697995776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5c305fe1b67de9fd15f2b14668490562441ab3772aa4f6b55405da569a7cd8b
3
+ size 2084892672
onnx/model_fp16.onnx_data_1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c599f18f950bd6b9306464b0500beb769e4f443c48410d7557a8702a3a5de20e
3
+ size 2063720448
onnx/model_fp16.onnx_data_2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fcf7693b163be40c8f761f0b1017bcbe91c779bfed92912369363fdfcf55e4a
3
+ size 2063720448
onnx/model_fp16.onnx_data_3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3450755dc9afb48dc5ce286cecb51ab3d01c006195c5394d6d2143554b69c617
3
+ size 1485662208
onnx/model_q4.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9af1b535d465ea1ddd9a8eb18f8e27a7df6eb45a51bec3dc820f1ff309891dd3
3
- size 284392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:612ee593ced3b2ef68285015829d4c390e5b747813ad1802508adee53297a41c
3
+ size 297813
onnx/model_q4.onnx_data_1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45d0f41ebcc6364e7f38736eff36120b784fbf6217f445857cdf81f09009aa9a
3
- size 1570516992
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cec4bdbc68288e38486fa8e653e8b49e882b92f3dd17e7cfab29cc1127fd3607
3
+ size 2065969152
onnx/model_q4f16.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ba424ab1c80f466ce3a96d64bcc61d73ae424d36fdb07fae94261f7b4ff1a2a
3
- size 286036
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:620f3a808b0219eb1a5bb8ff3a52adb829b7598232ac3b444446dc242874dac4
3
+ size 299123
onnx/model_q4f16.onnx_data CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75baf1a640e475f18ea4e0699ed2852824237befb802ad92a3e13660841b9566
3
- size 1569331200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89e17f87c1109f4d9f71350deb4104c05f90803a0b1f07d5e7fdd34b69e3ec24
3
+ size 2093094912
onnx/model_q4f16.onnx_data_1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:988b60599c0f9674cd44b0379b7306f304862296a123b0a503e75c5db3a5dd39
3
- size 1498152960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44838ae340ab4e836d488977aea082a9be1978800466a96a266c593bc947010e
3
+ size 974389248
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:382cc235b56c725945e149cc25f191da667c836655efd0857b004320e90e91ea
3
- size 15524095
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5ee8c0b1f9862ab7052a99edd2f8f3e69258b2d2670c5880bb44d3fc0599c4c
3
+ size 13303003
tokenizer_config.json CHANGED
@@ -101,12 +101,12 @@
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
- }
 
 
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
+ "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 %}"
112
+ }