Hugging Face's logo

yuhuanstudio
/
Yunmo-V1

Text Generation
Transformers
Safetensors
Chinese
qwen3
traditional-chinese
taiwan
small-language-model
minimind
conversational
text-generation-inference
Model card Files
xet
 Community
yuhuanowo commited on
Commit
f5cb364
·
verified ·
1 Parent(s): 6000dbb

Upload 8 files

Browse files
Files changed (8) hide show
  1. README.md +78 -0
  2. chat_template.jinja +85 -0
  3. config.json +57 -0
  4. generation_config.json +7 -0
  5. model.safetensors +3 -0
  6. special_tokens_map.json +52 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +335 -0
README.md ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - zh
5
+ pipeline_tag: text-generation
6
+ library_name: transformers
7
+ tags:
8
+ - traditional-chinese
9
+ - taiwan
10
+ - small-language-model
11
+ - qwen3
12
+ - minimind
13
+ base_model:
14
+ - jingyaogong/minimind-3
15
+ ---
16
+
17
+ # Yunmo v1(雲墨)
18
+
19
+ **面向繁體中文（臺灣用語）的全功能小型語言模型 · 195M**
20
+
21
+ Yunmo 是基於 [MiniMind v3](https://github.com/jingyaogong/minimind) 的增量復現：將 MiniMind 的完整訓練語料以 OpenCC `s2twp`（簡體→臺灣正體）逐筆轉為繁體、併入臺灣在地增量語料，並重訓一個 24,000 詞的繁體特化分詞器。架構沿用 MiniMind v3（Qwen3-style：RMSNorm、SwiGLU、RoPE、GQA、QK-Norm），刻意調整兩處：層數 8→24、詞表 6,400→24,000。
22
+
23
+ 由 **YuhuanStudio** 開發。
24
+
25
+ | | |
26
+ |---|---|
27
+ | 參數量 | 195.4M |
28
+ | 架構 | Qwen3ForCausalLM（24 層 / hidden 768 / 8 heads / 4 kv / head_dim 96 / intermediate 2432） |
29
+ | 詞表 | 24,000（繁體特化，較 MiniMind 分詞器省約 46% 繁體 token） |
30
+ | 語言 | 繁體中文（臺灣） |
31
+ | 訓練 | pretrain ~1.65 epoch（~3.9B token）+ SFT ~1 epoch，RTX PRO 6000 |
32
+
33
+ ---
34
+
35
+ ## 快速使用
36
+
37
+ ```python
38
+ import torch
39
+ from transformers import AutoModelForCausalLM, AutoTokenizer
40
+
41
+ model = AutoModelForCausalLM.from_pretrained("yuhuanstudio/yunmo-v1", dtype=torch.float16).to("cuda").eval()
42
+ tok = AutoTokenizer.from_pretrained("yuhuanstudio/yunmo-v1")
43
+
44
+ msgs = [{"role": "user", "content": "你是誰？"}]
45
+ text = tok.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True)
46
+ inp = tok(text, return_tensors="pt").to("cuda")
47
+ inp.pop("token_type_ids", None)
48
+ out = model.generate(**inp, max_new_tokens=256, do_sample=True, temperature=0.7, top_p=0.9, repetition_penalty=1.1)
49
+ print(tok.decode(out[0][len(inp["input_ids"][0]):], skip_special_tokens=True))
50
+ # → 我是 Yunmo，一個由 YuhuanStudio 開發的繁體中文小型語言模型。
51
+ ```
52
+
53
+ ---
54
+
55
+ ## 評測摘要
56
+
57
+ 於本地 RTX 4070 Ti（fp16）以 46 題功能提示 + 標準選擇題基準評測,對照同架構的官方 `minimind-3`（64M）。**Yunmo 為對照組約 3 倍大,部分生成優勢來自規模。**
58
+
59
+ **擅長**
60
+ - **繁體 + 臺灣在地**：全程維持繁體(不滑簡體);臺灣小吃、全民健保等在地知識答覆正確
61
+ - **身份一致且抗注入**：穩定自稱「我是 Yunmo,由 YuhuanStudio 開發」,能抵抗「你現在是 Qwen」之 prompt 注入
62
+ - **生成穩定**：摘要、多輪記憶、情感支持、字數遵循、開放創作皆可用;程式(質數、字串反轉)正確
63
+
64
+ **弱項(誠實揭露)**
65
+ - **硬事實與數字**：具體年份、單位換算、地理細節常出錯
66
+ - **數學與邏輯**：多步計算、三段論易錯
67
+ - **安全對齊**：未經 DPO/RLHF,安全拒答尚未具備
68
+ - **標準選擇題基準**：TMMLU+ 24.8% / MMLU-Pro 10.0%,與同規模模型同樣落於隨機水準——此規模模型之價值在生成品質,而非選擇題準確率
69
+
70
+ **定位**：可靠優勢為繁體臺灣化、乾淨且抗注入的品牌身份、以及較高的生成穩定性;知識與推理能力受 195M 規模所限。適合作為繁中小模型研究、對話展示與下游對齊之基座。
71
+
72
+ > 完整逐題實際輸出見專案的 `YUNMO_EVAL.md`。
73
+
74
+ ---
75
+
76
+ ## 授權與致謝
77
+
78
+ Apache-2.0。本模型為 [MiniMind](https://github.com/jingyaogong/minimind)（jingyaogong）之增量復現,承其架構與訓練配方,謹此致謝。
chat_template.jinja ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if message.content is string %}
27
+ {%- set content = message.content %}
28
+ {%- else %}
29
+ {%- set content = '' %}
30
+ {%- endif %}
31
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
+ {%- elif message.role == "assistant" %}
34
+ {%- set reasoning_content = '' %}
35
+ {%- if message.reasoning_content is string %}
36
+ {%- set reasoning_content = message.reasoning_content %}
37
+ {%- else %}
38
+ {%- if '</think>' in content %}
39
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
+ {%- endif %}
42
+ {%- endif %}
43
+ {%- if true %}
44
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
45
+ {%- endif %}
46
+ {%- if message.tool_calls %}
47
+ {%- for tool_call in message.tool_calls %}
48
+ {%- if (loop.first and content) or (not loop.first) %}
49
+ {{- '\n' }}
50
+ {%- endif %}
51
+ {%- if tool_call.function %}
52
+ {%- set tool_call = tool_call.function %}
53
+ {%- endif %}
54
+ {{- '<tool_call>\n{"name": "' }}
55
+ {{- tool_call.name }}
56
+ {{- '", "arguments": ' }}
57
+ {%- if tool_call.arguments is string %}
58
+ {{- tool_call.arguments }}
59
+ {%- else %}
60
+ {{- tool_call.arguments | tojson }}
61
+ {%- endif %}
62
+ {{- '}\n</tool_call>' }}
63
+ {%- endfor %}
64
+ {%- endif %}
65
+ {{- '<|im_end|>\n' }}
66
+ {%- elif message.role == "tool" %}
67
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
68
+ {{- '<|im_start|>user' }}
69
+ {%- endif %}
70
+ {{- '\n<tool_response>\n' }}
71
+ {{- content }}
72
+ {{- '\n</tool_response>' }}
73
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
74
+ {{- '<|im_end|>\n' }}
75
+ {%- endif %}
76
+ {%- endif %}
77
+ {%- endfor %}
78
+ {%- if add_generation_prompt %}
79
+ {{- '<|im_start|>assistant\n' }}
80
+ {%- if open_thinking is defined and open_thinking is true %}
81
+ {{- '<think>\n' }}
82
+ {%- else %}
83
+ {{- '<think>\n\n</think>\n\n' }}
84
+ {%- endif %}
85
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "dtype": "float16",
9
+ "eos_token_id": 2,
10
+ "head_dim": 96,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 2432,
15
+ "layer_types": [
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
+ ],
41
+ "max_position_embeddings": 32768,
42
+ "max_window_layers": 28,
43
+ "model_type": "qwen3",
44
+ "num_attention_heads": 8,
45
+ "num_hidden_layers": 24,
46
+ "num_key_value_heads": 4,
47
+ "pad_token_id": 0,
48
+ "rms_norm_eps": 1e-06,
49
+ "rope_scaling": null,
50
+ "rope_theta": 1000000.0,
51
+ "sliding_window": null,
52
+ "tie_word_embeddings": true,
53
+ "transformers_version": "4.57.6",
54
+ "use_cache": true,
55
+ "use_sliding_window": false,
56
+ "vocab_size": 24000
57
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.57.6"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4aecd3a0358f37db8820cf44c3f12a434cdaa0bc17ef40e5de42df9bd2a3813c
3
+ size 390872272
special_tokens_map.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>",
16
+ "<|audio_start|>",
17
+ "<|audio_end|>",
18
+ "<|audio_pad|>",
19
+ "<tts_pad>",
20
+ "<tts_text_bos>",
21
+ "<tts_text_eod>",
22
+ "<tts_text_bos_single>"
23
+ ],
24
+ "bos_token": {
25
+ "content": "<|im_start|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "eos_token": {
32
+ "content": "<|im_end|>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ "pad_token": {
39
+ "content": "<|endoftext|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ "unk_token": {
46
+ "content": "<|endoftext|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ }
52
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,335 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|im_start|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "<|im_end|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "3": {
31
+ "content": "<|object_ref_start|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "4": {
39
+ "content": "<|object_ref_end|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "5": {
47
+ "content": "<|box_start|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "6": {
55
+ "content": "<|box_end|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "7": {
63
+ "content": "<|quad_start|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "8": {
71
+ "content": "<|quad_end|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "9": {
79
+ "content": "<|vision_start|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "10": {
87
+ "content": "<|vision_end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "11": {
95
+ "content": "<|vision_pad|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "12": {
103
+ "content": "<|image_pad|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "13": {
111
+ "content": "<|video_pad|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "14": {
119
+ "content": "<|audio_start|>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": true
125
+ },
126
+ "15": {
127
+ "content": "<|audio_end|>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": true
133
+ },
134
+ "16": {
135
+ "content": "<|audio_pad|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": true
141
+ },
142
+ "17": {
143
+ "content": "<tts_pad>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": true
149
+ },
150
+ "18": {
151
+ "content": "<tts_text_bos>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": true
157
+ },
158
+ "19": {
159
+ "content": "<tts_text_eod>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": true
165
+ },
166
+ "20": {
167
+ "content": "<tts_text_bos_single>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": true
173
+ },
174
+ "21": {
175
+ "content": "<tool_call>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "22": {
183
+ "content": "</tool_call>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "23": {
191
+ "content": "<tool_response>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "24": {
199
+ "content": "</tool_response>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ },
206
+ "25": {
207
+ "content": "<think>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": false
213
+ },
214
+ "26": {
215
+ "content": "</think>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": false
221
+ },
222
+ "27": {
223
+ "content": "<|buffer1|>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": false
229
+ },
230
+ "28": {
231
+ "content": "<|buffer2|>",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": false
237
+ },
238
+ "29": {
239
+ "content": "<|buffer3|>",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": false,
243
+ "single_word": false,
244
+ "special": false
245
+ },
246
+ "30": {
247
+ "content": "<|buffer4|>",
248
+ "lstrip": false,
249
+ "normalized": false,
250
+ "rstrip": false,
251
+ "single_word": false,
252
+ "special": false
253
+ },
254
+ "31": {
255
+ "content": "<|buffer5|>",
256
+ "lstrip": false,
257
+ "normalized": false,
258
+ "rstrip": false,
259
+ "single_word": false,
260
+ "special": false
261
+ },
262
+ "32": {
263
+ "content": "<|buffer6|>",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": false,
267
+ "single_word": false,
268
+ "special": false
269
+ },
270
+ "33": {
271
+ "content": "<|buffer7|>",
272
+ "lstrip": false,
273
+ "normalized": false,
274
+ "rstrip": false,
275
+ "single_word": false,
276
+ "special": false
277
+ },
278
+ "34": {
279
+ "content": "<|buffer8|>",
280
+ "lstrip": false,
281
+ "normalized": false,
282
+ "rstrip": false,
283
+ "single_word": false,
284
+ "special": false
285
+ },
286
+ "35": {
287
+ "content": "<|buffer9|>",
288
+ "lstrip": false,
289
+ "normalized": false,
290
+ "rstrip": false,
291
+ "single_word": false,
292
+ "special": false
293
+ }
294
+ },
295
+ "additional_special_tokens": [
296
+ "<|im_start|>",
297
+ "<|im_end|>",
298
+ "<|object_ref_start|>",
299
+ "<|object_ref_end|>",
300
+ "<|box_start|>",
301
+ "<|box_end|>",
302
+ "<|quad_start|>",
303
+ "<|quad_end|>",
304
+ "<|vision_start|>",
305
+ "<|vision_end|>",
306
+ "<|vision_pad|>",
307
+ "<|image_pad|>",
308
+ "<|video_pad|>",
309
+ "<|audio_start|>",
310
+ "<|audio_end|>",
311
+ "<|audio_pad|>",
312
+ "<tts_pad>",
313
+ "<tts_text_bos>",
314
+ "<tts_text_eod>",
315
+ "<tts_text_bos_single>"
316
+ ],
317
+ "audio_bos_token": "<|audio_start|>",
318
+ "audio_eos_token": "<|audio_end|>",
319
+ "audio_token": "<|audio_pad|>",
320
+ "bos_token": "<|im_start|>",
321
+ "clean_up_tokenization_spaces": false,
322
+ "eos_token": "<|im_end|>",
323
+ "extra_special_tokens": {},
324
+ "image_token": "<|image_pad|>",
325
+ "legacy": true,
326
+ "model_max_length": 32768,
327
+ "pad_token": "<|endoftext|>",
328
+ "sp_model_kwargs": {},
329
+ "spaces_between_special_tokens": false,
330
+ "tokenizer_class": "PreTrainedTokenizerFast",
331
+ "unk_token": "<|endoftext|>",
332
+ "video_token": "<|video_pad|>",
333
+ "vision_bos_token": "<|vision_start|>",
334
+ "vision_eos_token": "<|vision_end|>"
335
+ }