Hugging Face's logo

BCCard
/
A.X-4.0-FP8-Dynamic

Safetensors
qwen2
compressed-tensors
Model card Files
xet
Community
sh2orc commited on
Commit
f5b8a22
·
verified ·
1 Parent(s): 622dbd8

Add files using upload-large-folder tool

Browse files
Files changed (27) hide show
  1. added_tokens.json +4 -0
  2. chat_template.jinja +72 -0
  3. config.json +157 -0
  4. generation_config.json +9 -0
  5. merges.txt +0 -0
  6. model-00001-of-00016.safetensors +3 -0
  7. model-00002-of-00016.safetensors +3 -0
  8. model-00003-of-00016.safetensors +3 -0
  9. model-00004-of-00016.safetensors +3 -0
  10. model-00005-of-00016.safetensors +3 -0
  11. model-00006-of-00016.safetensors +3 -0
  12. model-00007-of-00016.safetensors +3 -0
  13. model-00008-of-00016.safetensors +3 -0
  14. model-00009-of-00016.safetensors +3 -0
  15. model-00010-of-00016.safetensors +3 -0
  16. model-00011-of-00016.safetensors +3 -0
  17. model-00012-of-00016.safetensors +3 -0
  18. model-00013-of-00016.safetensors +3 -0
  19. model-00014-of-00016.safetensors +3 -0
  20. model-00015-of-00016.safetensors +3 -0
  21. model-00016-of-00016.safetensors +3 -0
  22. model.safetensors.index.json +0 -0
  23. recipe.yaml +6 -0
  24. special_tokens_map.json +88 -0
  25. tokenizer.json +0 -0
  26. tokenizer_config.json +401 -0
  27. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</think>": 102400,
3
+ "<think>": 102401
4
+ }
chat_template.jinja ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools is iterable and tools | length > 0 %}
2
+ {{- '<|im_start|><|system|>'}}
3
+ {{- '당신은 도구 호출 기능을 갖춘 유용한 도우미입니다. 사용자의 요청을 처리하기 위해서 필요한 도구가 주어진 목록에 있는 경우 도구 호출로 응답하세요.
4
+ 필요한 도구가 목록에 없는 경우에는 도구 호출 없이 사용자가 요구한 정보를 제공하세요.
5
+ 필요한 도구가 목록에 있지만 해당 도구를 호출하는데 필요한 argument 정보가 부족한 경우 해당 정보를 사용자에게 요청하세요.
6
+ 사용자의 요청을 처리하기 위해 여러번 도구를 호출할 수 있어야 합니다.
7
+ 도구 호출 이후 도구 실행 결과를 입력으로 받으면 해당 결과를 활용하여 답변을 생성하세요.
8
+
9
+ 다음은 접근할 수 있는 도구들의 목록 입니다:
10
+ <tools>
11
+ '}}
12
+ {%- for t in tools %}
13
+ {{- t | tojson }}
14
+ {{- '
15
+ ' }}
16
+ {%- endfor %}
17
+ {{- '</tools>' }}
18
+ {{- '
19
+
20
+ 도구를 호출하려면 아래의 JSON으로 응답하세요.
21
+ 도구 호출 형식: <tool_call>{"name": 도구 이름, "arguments": dictionary 형태의 도구 인자값}</tool_call>' }}
22
+ {{- '<|im_end|>' }}
23
+ {%- endif %}
24
+
25
+ {%- for message in messages %}
26
+ {%- if message.role == 'system' %}
27
+ {{- '<|im_start|><|system|>' + message.content + '<|im_end|>'}}
28
+ {%- elif message.role == 'user' %}
29
+ {{- '<|im_start|><|user|>' + message.content + '<|im_end|>'}}
30
+ {%- elif message.role == 'assistant' %}
31
+ {{- '<|im_start|><|assistant|>'}}
32
+ {%- set content = '' %}
33
+ {%- if message.content is defined %}
34
+ {%- set content = message.content %}
35
+ {%- endif %}
36
+
37
+ {%- if add_generation_prompt and not (message.reasoning_content is defined and message.reasoning_content is not none) %}
38
+ {%- if '</think>' in message.content %}
39
+ {%- set content = message.content.split('</think>'.strip())[-1].lstrip('\n') %}
40
+ {%- endif %}
41
+ {%- endif %}
42
+
43
+ {{- content}}
44
+ {%- if message.tool_calls is defined %}
45
+ {%- for tool_call in message.tool_calls %}
46
+ {%- if tool_call.function is defined %}
47
+ {%- set tool_call = tool_call.function %}
48
+ {%- endif %}
49
+ {{- '<tool_call>' }}
50
+ {{- '{' }}
51
+ {{- '"name": "' }}
52
+ {{- tool_call.name }}
53
+ {{- '"' }}
54
+ {%- if tool_call.arguments is defined %}
55
+ {{- ', ' }}
56
+ {{- '"arguments": ' }}
57
+ {{- tool_call.arguments|tojson }}
58
+ {%- endif %}
59
+ {{- '}' }}
60
+ {{- '</tool_call>' }}
61
+ {%- endfor %}
62
+ {%- endif %}
63
+ {{- '<|im_end|>'}}
64
+
65
+ {%- elif message.role == 'tool' %}
66
+ {{- '<|im_start|><|extra_id_13|><tool_output>' + message.content + '</tool_output><|im_end|>'}}
67
+ {%- endif %}
68
+ {%- endfor %}
69
+
70
+ {%- if add_generation_prompt %}
71
+ {{- '<|im_start|><|assistant|>' }}
72
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 0,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 8192,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 29568,
12
+ "layer_types": [
13
+ "full_attention",
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention",
73
+ "full_attention",
74
+ "full_attention",
75
+ "full_attention",
76
+ "full_attention",
77
+ "full_attention",
78
+ "full_attention",
79
+ "full_attention",
80
+ "full_attention",
81
+ "full_attention",
82
+ "full_attention",
83
+ "full_attention",
84
+ "full_attention",
85
+ "full_attention",
86
+ "full_attention",
87
+ "full_attention",
88
+ "full_attention",
89
+ "full_attention",
90
+ "full_attention",
91
+ "full_attention",
92
+ "full_attention"
93
+ ],
94
+ "max_position_embeddings": 131072,
95
+ "max_window_layers": 28,
96
+ "model_type": "qwen2",
97
+ "num_attention_heads": 64,
98
+ "num_hidden_layers": 80,
99
+ "num_key_value_heads": 8,
100
+ "quantization_config": {
101
+ "config_groups": {
102
+ "group_0": {
103
+ "input_activations": {
104
+ "actorder": null,
105
+ "block_structure": null,
106
+ "dynamic": true,
107
+ "group_size": null,
108
+ "num_bits": 8,
109
+ "observer": null,
110
+ "observer_kwargs": {},
111
+ "strategy": "token",
112
+ "symmetric": true,
113
+ "type": "float"
114
+ },
115
+ "output_activations": null,
116
+ "targets": [
117
+ "Linear"
118
+ ],
119
+ "weights": {
120
+ "actorder": null,
121
+ "block_structure": null,
122
+ "dynamic": false,
123
+ "group_size": null,
124
+ "num_bits": 8,
125
+ "observer": "minmax",
126
+ "observer_kwargs": {},
127
+ "strategy": "channel",
128
+ "symmetric": true,
129
+ "type": "float"
130
+ }
131
+ }
132
+ },
133
+ "format": "float-quantized",
134
+ "global_compression_ratio": null,
135
+ "ignore": [
136
+ "lm_head"
137
+ ],
138
+ "kv_cache_scheme": null,
139
+ "quant_method": "compressed-tensors",
140
+ "quantization_status": "compressed"
141
+ },
142
+ "rms_norm_eps": 1e-05,
143
+ "rope_scaling": {
144
+ "factor": 2.0,
145
+ "original_max_position_embeddings": 131072,
146
+ "rope_type": "yarn",
147
+ "type": "yarn"
148
+ },
149
+ "rope_theta": 5000000,
150
+ "sliding_window": null,
151
+ "tie_word_embeddings": false,
152
+ "torch_dtype": "bfloat16",
153
+ "transformers_version": "4.54.1",
154
+ "use_cache": false,
155
+ "use_sliding_window": false,
156
+ "vocab_size": 102400
157
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "do_sample": true,
4
+ "eos_token_id": 27,
5
+ "pad_token_id": 1,
6
+ "temperature": 0.6,
7
+ "top_p": 0.95,
8
+ "transformers_version": "4.54.1"
9
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ff5f4a40e60e24b80019f3a0a613e55f133fba3dc97bf970cf008fa2b64107e
3
+ size 4946991480
model-00002-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:160b092a1fe60a9efa374dbe21a289bb9cea1e35c930a582ff0aeb10a3b2debe
3
+ size 4782749264
model-00003-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3db661d3323052592d4cc9d3daa029ed2579747b5a4a7c59b45fe74fa58e5b02
3
+ size 4873986008
model-00004-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bc89828bc796c08941d26992557db57b3f9d0077ccabda73c38fda60eff4981
3
+ size 4782749368
model-00005-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dbeac4c1a546cd4c11b5d7e4c1b814456989940d9457db74fe036a9e32ecf22
3
+ size 4873986032
model-00006-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30868576ff59f107e94176d37df7ee1281e36aece37d1620231947ce75bdb466
3
+ size 4782749368
model-00007-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89b5de72a28944c056c6d70e7f65c11ec05b3c96715146f70a9b5846b271cd1e
3
+ size 4873986032
model-00008-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb7bcd2dd2cce648eb22bcef6c5fb69b2509bbc078747d16aed34e6791b07ecf
3
+ size 4782749368
model-00009-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:145b0885ac498c8d8f308055a38768e078487555da39360aa671d12cf9698bc9
3
+ size 4873986032
model-00010-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9f8b1b8aca84f268982f2bc00fad5b5907ce5c8c1df79f55d6d6aba2c0cbf0d
3
+ size 4782749368
model-00011-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c99983766f56d2c1e1559549308c953d832edc9543fd1659f7ba6976e9b165d
3
+ size 4873986032
model-00012-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62433ea9c1dae60a130ae51ffea4912e8d9b1b5476809f0b13a13e057cacd3ba
3
+ size 4782749368
model-00013-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a90e6e27460359b7662bff013f8654e4f6294c41ef785c6574e016a2234be9f
3
+ size 4873986032
model-00014-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24c2ef4f85dd0a9abf8db63058ea0cfa3f291fcca8d77470a3dac1bdeff6e480
3
+ size 4782749368
model-00015-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d6da2c3d3d1cc5923d33a1c44d016d86dbd9e4bf65e691793b4091416466cc7
3
+ size 4238388104
model-00016-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e905e870c873a9672de4e03f4843de19575f00308f003994e5860b1cb8b88771
3
+ size 1677721728
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
recipe.yaml ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ default_stage:
2
+ default_modifiers:
3
+ QuantizationModifier:
4
+ targets: [Linear]
5
+ ignore: [lm_head, 're:.*mlp.gate$', 're:.*mlp.shared_expert_gate$']
6
+ scheme: FP8_dynamic
special_tokens_map.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<|pad|>",
5
+ "<|unk|>",
6
+ "<|sep|>",
7
+ "<|mask|>",
8
+ "<|cls|>",
9
+ "<|image|>",
10
+ "<|audio|>",
11
+ "<|user|>",
12
+ "<|system|>",
13
+ "<|assistant|>",
14
+ "<|extra_id_0|>",
15
+ "<|extra_id_1|>",
16
+ "<|extra_id_2|>",
17
+ "<|extra_id_3|>",
18
+ "<|extra_id_4|>",
19
+ "<|extra_id_5|>",
20
+ "<|extra_id_6|>",
21
+ "<|extra_id_7|>",
22
+ "<|extra_id_8|>",
23
+ "<|extra_id_9|>",
24
+ "<|extra_id_10|>",
25
+ "<|extra_id_13|>",
26
+ "<|im_start|>",
27
+ "<|im_sep|>",
28
+ "<|im_end|>",
29
+ "<|resident_reg|>",
30
+ "<|foreigner_reg|>",
31
+ "<|business_reg|>",
32
+ "<|credit_card|>",
33
+ "<|passport|>",
34
+ "<|driver_license|>",
35
+ "<|telephone|>",
36
+ "<|health_insurance|>",
37
+ "<|bank_account|>"
38
+ ],
39
+ "bos_token": {
40
+ "content": "<|endoftext|>",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "cls_token": {
47
+ "content": "<|cls|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ "eos_token": {
54
+ "content": "<|im_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false
59
+ },
60
+ "mask_token": {
61
+ "content": "<|mask|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false
66
+ },
67
+ "pad_token": {
68
+ "content": "<|pad|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false
73
+ },
74
+ "sep_token": {
75
+ "content": "<|sep|>",
76
+ "lstrip": false,
77
+ "normalized": false,
78
+ "rstrip": false,
79
+ "single_word": false
80
+ },
81
+ "unk_token": {
82
+ "content": "<|unk|>",
83
+ "lstrip": false,
84
+ "normalized": false,
85
+ "rstrip": false,
86
+ "single_word": false
87
+ }
88
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,401 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<|pad|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<|unk|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<|sep|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<|mask|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "5": {
46
+ "content": "<|cls|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "6": {
54
+ "content": "<|image|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "7": {
62
+ "content": "<|audio|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "8": {
70
+ "content": "<|user|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "9": {
78
+ "content": "<|system|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "10": {
86
+ "content": "<|assistant|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "11": {
94
+ "content": "<|extra_id_0|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "12": {
102
+ "content": "<|extra_id_1|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "13": {
110
+ "content": "<|extra_id_2|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "14": {
118
+ "content": "<|extra_id_3|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "15": {
126
+ "content": "<|extra_id_4|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "16": {
134
+ "content": "<|extra_id_5|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "17": {
142
+ "content": "<|extra_id_6|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "18": {
150
+ "content": "<|extra_id_7|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "19": {
158
+ "content": "<|extra_id_8|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "20": {
166
+ "content": "<|extra_id_9|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "21": {
174
+ "content": "<|extra_id_10|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "22": {
182
+ "content": "<|extra_id_11|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "23": {
190
+ "content": "<|extra_id_12|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "24": {
198
+ "content": "<|extra_id_13|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "25": {
206
+ "content": "<|im_start|>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "26": {
214
+ "content": "<|im_sep|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "27": {
222
+ "content": "<|im_end|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "28": {
230
+ "content": "<|resident_reg|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "29": {
238
+ "content": "<|foreigner_reg|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "30": {
246
+ "content": "<|business_reg|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "31": {
254
+ "content": "<|credit_card|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "32": {
262
+ "content": "<|passport|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "33": {
270
+ "content": "<|driver_license|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "34": {
278
+ "content": "<|telephone|>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "35": {
286
+ "content": "<|health_insurance|>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "36": {
294
+ "content": "<|bank_account|>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "37": {
302
+ "content": "</tool_output>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": false
308
+ },
309
+ "38": {
310
+ "content": "<tool_output>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": false
316
+ },
317
+ "39": {
318
+ "content": "</tool_call>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": false
324
+ },
325
+ "40": {
326
+ "content": "<tool_call>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": false
332
+ },
333
+ "102400": {
334
+ "content": "</think>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": false
340
+ },
341
+ "102401": {
342
+ "content": "<think>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": false
348
+ }
349
+ },
350
+ "additional_special_tokens": [
351
+ "<|endoftext|>",
352
+ "<|pad|>",
353
+ "<|unk|>",
354
+ "<|sep|>",
355
+ "<|mask|>",
356
+ "<|cls|>",
357
+ "<|image|>",
358
+ "<|audio|>",
359
+ "<|user|>",
360
+ "<|system|>",
361
+ "<|assistant|>",
362
+ "<|extra_id_0|>",
363
+ "<|extra_id_1|>",
364
+ "<|extra_id_2|>",
365
+ "<|extra_id_3|>",
366
+ "<|extra_id_4|>",
367
+ "<|extra_id_5|>",
368
+ "<|extra_id_6|>",
369
+ "<|extra_id_7|>",
370
+ "<|extra_id_8|>",
371
+ "<|extra_id_9|>",
372
+ "<|extra_id_10|>",
373
+ "<|extra_id_13|>",
374
+ "<|im_start|>",
375
+ "<|im_sep|>",
376
+ "<|im_end|>",
377
+ "<|resident_reg|>",
378
+ "<|foreigner_reg|>",
379
+ "<|business_reg|>",
380
+ "<|credit_card|>",
381
+ "<|passport|>",
382
+ "<|driver_license|>",
383
+ "<|telephone|>",
384
+ "<|health_insurance|>",
385
+ "<|bank_account|>"
386
+ ],
387
+ "bos_token": "<|endoftext|>",
388
+ "clean_up_tokenization_spaces": true,
389
+ "cls_token": "<|cls|>",
390
+ "eod_token": "<|endoftext|>",
391
+ "eos_token": "<|im_end|>",
392
+ "errors": "replace",
393
+ "extra_special_tokens": {},
394
+ "mask_token": "<|mask|>",
395
+ "model_max_length": 131072,
396
+ "pad_token": "<|pad|>",
397
+ "sep_token": "<|sep|>",
398
+ "tokenizer_class": "GPT2Tokenizer",
399
+ "unk_token": "<|unk|>",
400
+ "vocab_size": 102400
401
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff