yj313069
/

yj313069 BigDong commited on
Commit
e0ddf2e
·
0 Parent(s):

Duplicate from openbmb/MiniCPM5-1B

Browse files

Co-authored-by: Yudong Wang <BigDong@users.noreply.huggingface.co>

.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
README-cn.md ADDED
@@ -0,0 +1,351 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - zh
5
+ - en
6
+ library_name: transformers
7
+ pipeline_tag: text-generation
8
+ tags:
9
+ - minicpm
10
+ - minicpm5
11
+ - llama
12
+ - text-generation
13
+ - long-context
14
+ - tool-calling
15
+ - on-device
16
+ - edge-ai
17
+ datasets:
18
+ - openbmb/Ultra-FineWeb
19
+ - openbmb/Ultra-FineWeb-L3
20
+ - openbmb/UltraData-Math
21
+ - openbmb/UltraData-SFT-2605
22
+ ---
23
+
24
+ <div align="center">
25
+ <img src="https://raw.githubusercontent.com/OpenBMB/MiniCPM/main/assets/minicpm_logo.png" width="500em" />
26
+ </div>
27
+
28
+ <p align="center">
29
+ <a href="https://arxiv.org/pdf/2506.07900" target="_blank">MiniCPM 技术报告</a> |
30
+ <a href="https://github.com/OpenBMB/MiniCPM" target="_blank">GitHub 仓库</a> |
31
+ <a href="https://ultradata.openbmb.cn/" target="_blank">UltraData</a> |
32
+ <a href="https://github.com/OpenBMB/MiniCPM-Desk-Pet" target="_blank">MiniCPM 桌宠</a> |
33
+ <a href="https://huggingface.co/spaces/openbmb/MiniCPM5-1B-Demo" target="_blank">在线 Demo</a>
34
+ </p>
35
+
36
+ <p align="center">
37
+ <a href="https://huggingface.co/openbmb/MiniCPM5-1B/blob/main/README.md" target="_blank">English</a> |
38
+ 中文
39
+ </p>
40
+
41
+ ## 亮点
42
+
43
+ 我们正式发布 **MiniCPM5-1B**,这是 **MiniCPM5** 系列的首个模型。它是一款面向端侧、本地部署和资源受限场景的 1B 稠密 Transformer,能够达到同尺寸开源模型 SOTA 水平。
44
+
45
+ 🏆 **同尺寸开源模型 SOTA**:与同尺寸优秀开源模型相比,MiniCPM5-1B 在该对比范围内达到 SOTA 水平,优势主要体现在 Agentic 工具调用、代码生成和高难推理。
46
+
47
+ ![MiniCPM5-1B 各领域能力对比](https://raw.githubusercontent.com/OpenBMB/MiniCPM/main/assets/minicpm5/public_leaderboard_radar_cn.png)
48
+
49
+ 🧠 **双模式推理**:内置 `<think>` chat template,可通过 `enable_thinking` 在思考模式和非思考模式之间切换。同一份权重既可以作为快速助手,也可以承担更复杂的推理任务。
50
+
51
+ 🛠️ **部署 / 微调资源**:MiniCPM GitHub 仓库提供面向主要推理后端和微调框架的单页 cookbook,并配套 Agent Skills,方便复现部署和微调流程。
52
+
53
+ 🐱 **桌宠**:我们也提供了由 MiniCPM5-1B 本地驱动的桌宠应用。
54
+
55
+ ## 模型列表
56
+
57
+ 你可以按运行环境选择对应模型格式:
58
+
59
+ - **[MiniCPM5-1B](https://huggingface.co/openbmb/MiniCPM5-1B)** · [ModelScope](https://www.modelscope.cn/models/OpenBMB/MiniCPM5-1B) · BF16 正式版(经 RL + OPD 后训练) **👈 当前页面**
60
+ - **[MiniCPM5-1B-SFT](https://huggingface.co/openbmb/MiniCPM5-1B-SFT)** · [ModelScope](https://www.modelscope.cn/models/OpenBMB/MiniCPM5-1B-SFT) · BF16 SFT 单独 checkpoint(RL / OPD 之前)
61
+ - **[MiniCPM5-1B-Base](https://huggingface.co/openbmb/MiniCPM5-1B-Base)** · [ModelScope](https://www.modelscope.cn/models/OpenBMB/MiniCPM5-1B-Base) · BF16 base checkpoint(仅预训练)
62
+ - **[MiniCPM5-1B-GGUF](https://huggingface.co/openbmb/MiniCPM5-1B-GGUF)** · [ModelScope](https://www.modelscope.cn/models/OpenBMB/MiniCPM5-1B-GGUF) · GGUF,适用于 llama.cpp / Ollama / LM Studio
63
+ - **[MiniCPM5-1B-MLX](https://huggingface.co/openbmb/MiniCPM5-1B-MLX)** · [ModelScope](https://www.modelscope.cn/models/OpenBMB/MiniCPM5-1B-MLX) · MLX / 4bit,适用于 Apple Silicon
64
+
65
+ ## 模型信息
66
+
67
+ MiniCPM5-1B 具有以下特性:
68
+
69
+ - **类型**:Causal Language Model
70
+ - **架构**:标准 `LlamaForCausalLM`
71
+ - **参数数量**:1,080,632,832
72
+ - **非嵌入参数数量**:679,552,512
73
+ - **层数**:24
74
+ - **注意力头(GQA)**:16 个 Q heads / 2 个 KV heads
75
+ - **上下文长度**:131,072
76
+
77
+ ## 简介
78
+
79
+ MiniCPM5-1B 是 MiniCPM5 系列的首个模型,面向本地助手、coding agent、工具调用流程以及需要紧凑模型的推理场景。它在较小部署成本下提供原生长上下文能力,并通过同一份权重支持 Think / No Think 两种对话模式。
80
+
81
+ ## 评测结果
82
+
83
+ 我们选取 **LFM2.5-1.2B-Thinking**、**Qwen3-0.6B/think**、**Qwen3.5-0.8B/think** 等同尺寸优秀开源模型进行横向比较。这些模型本身已经很强;在这组对比中,MiniCPM5-1B 达到同尺寸开源模型 SOTA 水平,优势主要体现在工具调用、代码生成和高难推理上,也更适合承担本地 coding agent、工具助手和推理助手的角色。
84
+
85
+ ![MiniCPM-5 1B 基准评测成绩](https://raw.githubusercontent.com/OpenBMB/MiniCPM/main/assets/minicpm5/public_leaderboard_cn.png)
86
+
87
+ ## 训练流程
88
+
89
+ MiniCPM5-1B 的训练过程是 **[UltraData 分级数据管理体系](https://arxiv.org/pdf/2602.09003)** 的一次完整实践,覆盖 base training、mid-training 与后训练三个阶段。
90
+
91
+ **Base training** 采用逐级推进的训练配方,包含 stable training 与 decay training,用于建立基础语言能力与训练稳定性。随后进入 **mid-training**,进一步强化目标能力并适配数据分布。训练语料来自我们同步开源的 [Ultra-FineWeb](https://huggingface.co/datasets/openbmb/Ultra-FineWeb)、[Ultra-FineWeb-L3](https://huggingface.co/datasets/openbmb/Ultra-FineWeb-L3) 与 [UltraData-Math](https://huggingface.co/datasets/openbmb/UltraData-Math)。
92
+
93
+ **后训练阶段**分为 **SFT**、**RL** 与 **OPD** 三步。我们先使用 **200B tokens deep-thinking SFT** 与 **200B tokens hybrid-thinking SFT** 建立深度思考、混合思考和通用对话能力,相关 SFT 数据已同步开源为 [UltraData-SFT-2605](https://huggingface.co/datasets/openbmb/UltraData-SFT-2605)。随后针对数学、代码、闭卷问答和写作等方向训练专用 **RL teacher**,并通过 **On-Policy Distillation (OPD)** 将这些 teacher 的能力蒸馏回同一个发布模型。
94
+
95
+ ![MiniCPM5-1B 训练流程](https://raw.githubusercontent.com/OpenBMB/MiniCPM/main/assets/minicpm5/training_recipe.png)
96
+
97
+ ### RL + OPD 带来了什么?
98
+
99
+ **RL + OPD** 是 MiniCPM5-1B 后训练中的关键环节。在数学、代码、指令跟随三类任务上,RL + OPD 将平均分提升 **↑16 分**,同时将回复触顶 max-tokens 预算的比例降低 **↓29 个百分点**。下方图示展示 Reasoning RL 两阶段流程、分数提升和超长率下降。
100
+
101
+ **RL** 阶段组合了推理、闭卷问答、写作、指令跟随、长上下文理解和通用对话等多类互补训练信号。Reasoning RL 基于 [DAPO-Math-17k](https://huggingface.co/datasets/BytedTsinghua-SIA/DAPO-Math-17k) (借鉴 [JustRL](https://arxiv.org/pdf/2512.16649) 极简配方思想),并采用两阶段长度调度,以减少过长回复的同时提升推理准确性。我们还使用 [TriviaQA](https://huggingface.co/datasets/mandarjoshi/trivia_qa)、[NQ-Open](https://huggingface.co/datasets/google-research-datasets/nq_open)、[LongWriter-Zero-RLData](https://huggingface.co/datasets/THU-KEG/LongWriter-Zero-RLData)、合成可验证 RLVR 数据与 pair-wise RLHF 信号,提升可靠性、指令跟随和用户体验。
102
+
103
+ ![MiniCPM5-1B RL 两阶段流程](https://raw.githubusercontent.com/OpenBMB/MiniCPM/main/assets/minicpm5/rl_two_stage_overview.png)
104
+
105
+ **OPD** 阶段参考 Thinking Machines Lab 的 [On-Policy Distillation](https://thinkingmachines.ai/blog/on-policy-distillation/) 思路,并结合 [Rethinking On-Policy Distillation](https://arxiv.org/pdf/2604.13016) 做了实现改进。我们在强化学习框架中使用反向 KL 散度作为优势估计值,替代原有的 verification-based advantage;同时在 response 序列的每个位置分别对学生模型和教师模型 logits 做双边 top-k 采样,取并集后计算反向 KL 散度,以平衡监督信号准确性和训练效率。OPD 直接复用各 RL teacher 训练时的同分布 prompt 作为蒸馏数据,无需额外构造语料。
106
+
107
+ ![MiniCPM5-1B RL + OPD 增益](https://raw.githubusercontent.com/OpenBMB/MiniCPM/main/assets/minicpm5/rl_gains.png)
108
+
109
+ ![MiniCPM5-1B RL + OPD 超长率下降](https://raw.githubusercontent.com/OpenBMB/MiniCPM/main/assets/minicpm5/rl_overlong.png)
110
+
111
+ ## 快速上手
112
+
113
+ ### vLLM
114
+
115
+ ```bash
116
+ pip install "vllm>=0.21"
117
+ vllm serve openbmb/MiniCPM5-1B --port 8000
118
+ ```
119
+
120
+ ```bash
121
+ curl http://localhost:8000/v1/chat/completions \
122
+ -H "Content-Type: application/json" \
123
+ -d '{
124
+ "model": "openbmb/MiniCPM5-1B",
125
+ "messages": [{"role": "user", "content": "你是谁?可以简单介绍一下自己吗?"}],
126
+ "max_tokens": 128,
127
+ "temperature": 0.7
128
+ }'
129
+ ```
130
+
131
+ ### SGLang
132
+
133
+ ```bash
134
+ pip install "sglang[srt]>=0.5.12"
135
+ python -m sglang.launch_server --model-path openbmb/MiniCPM5-1B --port 30000
136
+ ```
137
+
138
+ ```bash
139
+ curl http://localhost:30000/v1/chat/completions \
140
+ -H "Content-Type: application/json" \
141
+ -d '{
142
+ "model": "openbmb/MiniCPM5-1B",
143
+ "messages": [{"role": "user", "content": "你是谁?可以简单介绍一下自己吗?"}],
144
+ "max_tokens": 128,
145
+ "temperature": 0.7
146
+ }'
147
+ ```
148
+
149
+ ### Transformers
150
+
151
+ ```bash
152
+ pip install -U "transformers>=5.6" accelerate torch
153
+ ```
154
+
155
+ ```python
156
+ from transformers import AutoModelForCausalLM, AutoTokenizer
157
+
158
+ model_id = "openbmb/MiniCPM5-1B"
159
+ tokenizer = AutoTokenizer.from_pretrained(model_id)
160
+ model = AutoModelForCausalLM.from_pretrained(
161
+ model_id,
162
+ torch_dtype="auto",
163
+ device_map="auto",
164
+ )
165
+
166
+ messages = [{"role": "user", "content": "你是谁?可以简单介绍一下自己吗?"}]
167
+ inputs = tokenizer.apply_chat_template(
168
+ messages,
169
+ tokenize=True,
170
+ add_generation_prompt=True,
171
+ enable_thinking=False,
172
+ return_dict=True,
173
+ return_tensors="pt",
174
+ ).to(model.device)
175
+
176
+ outputs = model.generate(**inputs, max_new_tokens=128)
177
+ print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
178
+ ```
179
+
180
+ 推荐的 chat template 采样参数:
181
+
182
+ | 模式 | 推荐采样参数 | 启用方式 |
183
+ | --- | --- | --- |
184
+ | **Think** | `temperature=0.9, top_p=0.95` | `enable_thinking=True` |
185
+ | **No Think** | `temperature=0.7, top_p=0.95` | `enable_thinking=False` |
186
+
187
+ ## 工具调用
188
+
189
+ 工具调用**推荐使用 SGLang**。MiniCPM5-1B 以 XML 格式产出工具调用,SGLang 内置的 `minicpm5` parser 会自动将其转换为 OpenAI 兼容的 `tool_calls` 字段。
190
+
191
+ ```bash
192
+ python -m sglang.launch_server --model-path openbmb/MiniCPM5-1B --port 30000 \
193
+ --tool-call-parser minicpm5 # 或:--tool-call-parser auto
194
+ ```
195
+
196
+ ## GitHub Cookbooks 与 Agent Skills
197
+
198
+ MiniCPM5-1B 使用**标准 `LlamaForCausalLM` 架构**,主流推理引擎可直接加载,**无需自定义算子,也无模型代码 fork**。逐步部署和微调说明请参考下方 GitHub cookbooks;Agent Skills 作为 GitHub 资源提供给使用 Cursor / Claude Code 类 coding agent 的用户。
199
+
200
+ ### 部署
201
+
202
+ | 后端 | 模型格式 / 适用场景 | Cookbook | Agent Skill |
203
+ | --- | --- | --- | --- |
204
+ | Transformers | BF16 / FP16,本地 Python 推理,GPU + CPU | [transformers.md](https://github.com/OpenBMB/MiniCPM/blob/main/docs/deployment/transformers.md) | [minicpm5-deploy-transformers](https://github.com/OpenBMB/MiniCPM/blob/main/skills/minicpm5-deploy-transformers/SKILL.md) |
205
+ | vLLM | BF16 / FP16 OpenAI server | [vllm.md](https://github.com/OpenBMB/MiniCPM/blob/main/docs/deployment/vllm.md) | [minicpm5-deploy-vllm](https://github.com/OpenBMB/MiniCPM/blob/main/skills/minicpm5-deploy-vllm/SKILL.md) |
206
+ | SGLang | BF16 / FP16 OpenAI server,推荐用于 tool calling | [sglang.md](https://github.com/OpenBMB/MiniCPM/blob/main/docs/deployment/sglang.md) | [minicpm5-deploy-sglang](https://github.com/OpenBMB/MiniCPM/blob/main/skills/minicpm5-deploy-sglang/SKILL.md) |
207
+ | llama.cpp | GGUF,CPU/GPU 本地推理 | [llama_cpp.md](https://github.com/OpenBMB/MiniCPM/blob/main/docs/deployment/llama_cpp.md) | [minicpm5-deploy-llama-cpp](https://github.com/OpenBMB/MiniCPM/blob/main/skills/minicpm5-deploy-llama-cpp/SKILL.md) |
208
+ | Ollama | GGUF,本地端侧运行 | [ollama.md](https://github.com/OpenBMB/MiniCPM/blob/main/docs/deployment/ollama.md) | [minicpm5-deploy-ollama](https://github.com/OpenBMB/MiniCPM/blob/main/skills/minicpm5-deploy-ollama/SKILL.md) |
209
+ | LM Studio | GGUF,Mac 桌面应用与 OpenAI server | [lmstudio.md](https://github.com/OpenBMB/MiniCPM/blob/main/docs/deployment/lmstudio.md) | [minicpm5-deploy-lmstudio](https://github.com/OpenBMB/MiniCPM/blob/main/skills/minicpm5-deploy-lmstudio/SKILL.md) |
210
+ | MLX | MLX / 4bit,Apple Silicon 本地推理 | [mlx.md](https://github.com/OpenBMB/MiniCPM/blob/main/docs/deployment/mlx.md) | [minicpm5-deploy-mlx](https://github.com/OpenBMB/MiniCPM/blob/main/skills/minicpm5-deploy-mlx/SKILL.md) |
211
+ | ArcLight | GGUF 本地端侧 / CPU / 桌面 / 服务器 | [arclight.md](https://github.com/OpenBMB/MiniCPM/blob/main/docs/deployment/arclight.md) | [minicpm5-deploy-arclight](https://github.com/OpenBMB/MiniCPM/blob/main/skills/minicpm5-deploy-arclight/SKILL.md) |
212
+
213
+ ### 微调
214
+
215
+ | 框架 | 适用场景 | Cookbook | Agent Skill |
216
+ | --- | --- | --- | --- |
217
+ | TRL + PEFT | LoRA / SFT 微调 | [trl.md](https://github.com/OpenBMB/MiniCPM/blob/main/docs/finetune/trl.md) | [minicpm5-finetune-trl](https://github.com/OpenBMB/MiniCPM/blob/main/skills/minicpm5-finetune-trl/SKILL.md) |
218
+ | LLaMA-Factory | 微调 | [llamafactory.md](https://github.com/OpenBMB/MiniCPM/blob/main/docs/finetune/llamafactory.md) | [minicpm5-finetune-llamafactory](https://github.com/OpenBMB/MiniCPM/blob/main/skills/minicpm5-finetune-llamafactory/SKILL.md) |
219
+ | ms-swift | 微调 | [ms_swift.md](https://github.com/OpenBMB/MiniCPM/blob/main/docs/finetune/ms_swift.md) | [minicpm5-finetune-ms-swift](https://github.com/OpenBMB/MiniCPM/blob/main/skills/minicpm5-finetune-ms-swift/SKILL.md) |
220
+ | unsloth | 微调 | [unsloth.md](https://github.com/OpenBMB/MiniCPM/blob/main/docs/finetune/unsloth.md) | [minicpm5-finetune-unsloth](https://github.com/OpenBMB/MiniCPM/blob/main/skills/minicpm5-finetune-unsloth/SKILL.md) |
221
+ | xtuner | 微调 | [xtuner.md](https://github.com/OpenBMB/MiniCPM/blob/main/docs/finetune/xtuner.md) | [minicpm5-finetune-xtuner](https://github.com/OpenBMB/MiniCPM/blob/main/skills/minicpm5-finetune-xtuner/SKILL.md) |
222
+
223
+ ### 其他支持的框架
224
+
225
+ 除上文列出的部署与微调框架外,MiniCPM5-1B 也支持通过 FlagOS 进行多芯片部署。
226
+
227
+ #### FlagOS 介绍
228
+
229
+ 为解决不同 AI 芯片大规模落地应用,北京智源研究院联合众多科研机构、芯片企业、系统厂商、算法和软件相关单位等国内外机构共同发起并创立了 FlagOS 开源社区。
230
+
231
+ FlagOS 社区致力于打造面向多种 AI 芯片的统一、开源的系统软件栈,包括大型算子库、统一AI编译器、并行训推框架、统一通信库等核心开源项目,构建「模型-系统-芯片」三层贯通的开放技术生态,通过“一次开发跨芯迁移”释放硬件计算潜力,打破不同芯片软件栈之间生态隔离,有效降低开发者的迁移成本。FlagOS 社区构建人工智能软硬件生态,突破单一闭源垄断,推动AI硬件技术大范围落地发展,立足中国、拥抱全球合作。
232
+
233
+ 官网速递:[https://flagos.io](https://flagos.io/)
234
+
235
+ <details>
236
+ <summary>FlagOS 多 AI 芯片支持与使用方式</summary>
237
+
238
+ #### FlagOS 多 AI 芯片支持
239
+
240
+ 基于 FlagOS 极短时间内适配 MiniCPM5-1B 到 9 种不同的 AI 芯片,得益于众智 FlagOS 的多芯片统一 AI 系统软件栈的能力。��前,在 FlagOS 团队构建的面向多架构人工智能芯片的大模型自动迁移、适配与发布平台 FlagRelease 上,已发布 MiniCPM5-1B 的多芯片版本。细节如下:
241
+
242
+ |Vendor|ModelScope|Huggingface|
243
+ |---|---|---|
244
+ |Nvidia|[MiniCPM5-1B-nvidia-FlagOS](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-nvidia-FlagOS)|[MiniCPM5-1B-nvidia-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-nvidia-FlagOS)|
245
+ |Hygon|[MiniCPM5-1B-hygon-FlagOS](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-hygon-FlagOS)|[MiniCPM5-1B-hygon-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-hygon-FlagOS)|
246
+ |Metax|[MiniCPM5-1B-metax-FlagOS](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-metax-FlagOS)|[MiniCPM5-1B-metax-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-metax-FlagOS)|
247
+ |Iluvatar|[MiniCPM5-1B-iluvatar-FlagOS](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-iluvatar-FlagOS)|[MiniCPM5-1B-iluvatar-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-iluvatar-FlagOS)|
248
+ |Zhenwu|[MiniCPM5-1B-zhenwu-FlagOS](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-zhenwu-FlagOS)|[MiniCPM5-1B-zhenwu-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-zhenwu-FlagOS)|
249
+ |Mthreads|[MiniCPM5-1B-mthreads-FlagOS](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-mthreads-FlagOS)|[MiniCPM5-1B-mthreads-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-mthreads-FlagOS)|
250
+ |Kunlunxin|[MiniCPM5-1B-kunlunxin-FlagOS](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-kunlunxin-FlagOS)|[MiniCPM5-1B-kunlunxin-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-kunlunxin-FlagOS)|
251
+ |Ascend|[MiniCPM5-1B-ascend-FlagOS](https://modelscope.cn/models/FlagRelease/MiniCPM5-1B-ascend-FlagOS)|[MiniCPM5-1B-ascend-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-ascend-FlagOS)|
252
+ |ARM-v9|[MiniCPM5-1B-Armv9-FlagOS](https://modelscope.cn/models/FlagRelease/MiniCPM5-1B-Armv9-FlagOS)|[MiniCPM5-1B-Armv9-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-Armv9-FlagOS)|
253
+
254
+ #### FlagOS 使用方式
255
+
256
+ ##### 使用 FlagOS 在 Nvidia 体验性能加速
257
+
258
+ ###### From FlagRelease(**推荐**)
259
+
260
+ FlagRelease是FlagOS团队构建的一套面向多架构人工智能芯片的大模型自动迁移、适配与发布平台,已发布MiniCPM-1B的多芯片版本。FlagRelase已内置相关软件包,无需用户安装。
261
+
262
+ ###### FlagRelease 镜像关键版本信息
263
+
264
+ ###### FlagRelease 使用速递
265
+
266
+ |Vendor|ModelScope|Huggingface|
267
+ |---|---|---|
268
+ |Nvidia|[MiniCPM5-1B-nvidia-FlagOS](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-nvidia-FlagOS)|[MiniCPM5-1B-nvidia-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-nvidia-FlagOS)|
269
+ |Hygon|[MiniCPM5-1B-hygon-FlagOS](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-hygon-FlagOS)|[MiniCPM5-1B-hygon-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-hygon-FlagOS)|
270
+ |Metax|[MiniCPM5-1B-metax-FlagOS](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-metax-FlagOS)|[MiniCPM5-1B-metax-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-metax-FlagOS)|
271
+ |Iluvatar|[MiniCPM5-1B-iluvatar-FlagOS](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-iluvatar-FlagOS)|[MiniCPM5-1B-iluvatar-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-iluvatar-FlagOS)|
272
+ |Zhenwu|[MiniCPM5-1B-zhenwu-FlagOS](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-zhenwu-FlagOS)|[MiniCPM5-1B-zhenwu-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-zhenwu-FlagOS)|
273
+ |Mthreads|[MiniCPM5-1B-mthreads-FlagOS](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-mthreads-FlagOS)|[MiniCPM5-1B-mthreads-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-mthreads-FlagOS)|
274
+ |Kunlunxin|[MiniCPM5-1B-kunlunxin-FlagOS](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-kunlunxin-FlagOS)|[MiniCPM5-1B-kunlunxin-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-kunlunxin-FlagOS)|
275
+ |Ascend|[MiniCPM5-1B-ascend-FlagOS](https://modelscope.cn/models/FlagRelease/MiniCPM5-1B-ascend-FlagOS)|[MiniCPM5-1B-ascend-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-ascend-FlagOS)|
276
+ |ARM-v9|[MiniCPM5-1B-Armv9-FlagOS](https://modelscope.cn/models/FlagRelease/MiniCPM5-1B-Armv9-FlagOS)|[MiniCPM5-1B-Armv9-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-Armv9-FlagOS)|
277
+
278
+ ###### 从零开始
279
+
280
+ - 依赖Python3.12, GLIBC_2.39, GLIBCXX_3.4.33, CXXABI_1.3.15 环境
281
+
282
+ ###### Vllm 版本
283
+
284
+ ###### 安装 FlagOS 算子库
285
+
286
+ 官方仓库:https://github.com/flagos-ai/FlagGems
287
+
288
+ ```PowerShell
289
+ pip install flag-gems==4.2.1rc0
290
+ pip install triton==3.5.1
291
+ ```
292
+
293
+ ###### 开启加速
294
+
295
+ 通过在vllm执行推理的源码中增加flagGems的导入即可开启flagGems加速
296
+
297
+ ```Bash
298
+ import flag_gems
299
+ flag_gems.enable(record=True, once=True, path="/root/gems.txt")
300
+ ```
301
+
302
+ ```Bash
303
+ vllm serve ${model_path} \
304
+ --trust-remote-code \
305
+ --dtype bfloat16 \
306
+ --enforce-eager \
307
+ --port ${Port} \
308
+ --served-model-name ${model_name} \
309
+ --gpu-memory-utilization 0.85
310
+ ```
311
+
312
+ ##### 使用 FlagOS 统一多芯片后端插件
313
+
314
+ **[vllm-plugin-FL](https://github.com/flagos-ai/vllm-plugin-FL)** 是一个为 **vLLM** 推理/服务框架构建的插件,它基于 **FlagOS 的统一多芯片后端**开发,旨在扩展 vLLM 在多种硬件环境下的功能和性能表现。
315
+
316
+ ###### vllm-plugin-FL 使用
317
+
318
+ |厂商|从零开始|从 FlagRelease 开始||
319
+ |---|---|---|---|
320
+ |英伟达|[vllm-plugin-FL/MiniCPM5-1B](https://github.com/flagos-ai/vllm-plugin-FL/blob/main/examples/minicpm/README.md)|[MiniCPM5-1B-ModelScope](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-nvidia-FlagOS)|[MiniCPM5-1B-nvidia-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-nvidia-FlagOS)|
321
+
322
+ </details>
323
+
324
+ ## 桌宠
325
+
326
+ 我们也发布了 **[OpenBMB/MiniCPM-Desk-Pet](https://github.com/OpenBMB/MiniCPM-Desk-Pet)**,一个由 MiniCPM5-1B 本地驱动的桌宠应用。它支持 Apple Silicon / NVIDIA GPU / CPU 路线,可以与 Cursor、Claude Code、Codex 等 coding agent 联动,并支持 LoRA 人格切换。
327
+
328
+ <a href="https://youtu.be/Ee0slMW8SEk"><img src="https://img.youtube.com/vi/Ee0slMW8SEk/0.jpg" alt="MiniCPM Desk Pet video demo" width="720"></a>
329
+
330
+ ## 局限性与负责任使用
331
+
332
+ MiniCPM5-1B 是一个基于训练数据统计规律生成文本的语言模型,可能生成不准确、有偏见或不安全的内容。在高风险场景中使用前,应对模型输出进行审查和验证。
333
+
334
+ 用户需要自行评估模型输出,配置必要的安全防护,并遵守适用法律法规和平台政策。
335
+
336
+ ## 开源协议
337
+
338
+ MiniCPM 模型权重与相关代码依照 [Apache-2.0](https://github.com/OpenBMB/MiniCPM/blob/main/LICENSE) 协议发布。
339
+
340
+ ## 引用
341
+
342
+ 如果觉得我们的工作有帮助,请引用:
343
+
344
+ ```bibtex
345
+ @article{minicpm4,
346
+ title={Minicpm4: Ultra-efficient llms on end devices},
347
+ author={MiniCPM, Team},
348
+ journal={arXiv preprint arXiv:2506.07900},
349
+ year={2025}
350
+ }
351
+ ```
README.md ADDED
@@ -0,0 +1,351 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ - zh
6
+ library_name: transformers
7
+ pipeline_tag: text-generation
8
+ tags:
9
+ - minicpm
10
+ - minicpm5
11
+ - llama
12
+ - text-generation
13
+ - long-context
14
+ - tool-calling
15
+ - on-device
16
+ - edge-ai
17
+ datasets:
18
+ - openbmb/Ultra-FineWeb
19
+ - openbmb/Ultra-FineWeb-L3
20
+ - openbmb/UltraData-Math
21
+ - openbmb/UltraData-SFT-2605
22
+ ---
23
+
24
+ <div align="center">
25
+ <img src="https://raw.githubusercontent.com/OpenBMB/MiniCPM/main/assets/minicpm_logo.png" width="500em" />
26
+ </div>
27
+
28
+ <p align="center">
29
+ <a href="https://arxiv.org/pdf/2506.07900" target="_blank">MiniCPM Tech Report</a> |
30
+ <a href="https://github.com/OpenBMB/MiniCPM" target="_blank">GitHub Repo</a> |
31
+ <a href="https://ultradata.openbmb.cn/" target="_blank">UltraData</a> |
32
+ <a href="https://github.com/OpenBMB/MiniCPM-Desk-Pet" target="_blank">MiniCPM Desk Pet</a> |
33
+ <a href="https://huggingface.co/spaces/openbmb/MiniCPM5-1B-Demo" target="_blank">Online Demo</a>
34
+ </p>
35
+
36
+ <p align="center">
37
+ English |
38
+ <a href="https://huggingface.co/openbmb/MiniCPM5-1B/blob/main/README-cn.md" target="_blank">中文</a>
39
+ </p>
40
+
41
+ ## Highlights
42
+
43
+ We are releasing **MiniCPM5-1B**, the first model in the **MiniCPM5** series. It is a dense 1B Transformer built for on-device, local deployment, and resource-constrained scenarios, reaching 1B-class open-source SOTA.
44
+
45
+ 🏆 **1B-class open-source SOTA**: compared with strong open-source models in the same size class, MiniCPM5-1B reaches SOTA within this comparison set. Its advantage is most visible in agentic tool use, code generation, and difficult reasoning.
46
+
47
+ ![MiniCPM5-1B capability comparison by domain](https://raw.githubusercontent.com/OpenBMB/MiniCPM/main/assets/minicpm5/public_leaderboard_radar_en.png)
48
+
49
+ 🧠 **Hybrid Reasoning**: built-in `<think>` chat template, switch via `enable_thinking`. The same checkpoint serves as both a fast assistant and a deliberate reasoner.
50
+
51
+ 🛠️ **Deployment / Fine-tuning Resources**: the MiniCPM GitHub repo provides single-page cookbooks and Agent Skills for major inference backends and fine-tuning frameworks.
52
+
53
+ 🐱 **Desktop Pet**: a local-LLM desktop pet driven by MiniCPM5-1B.
54
+
55
+ ## Model List
56
+
57
+ Use this directory to choose the model format that matches your runtime:
58
+
59
+ - **[MiniCPM5-1B](https://huggingface.co/openbmb/MiniCPM5-1B)** · [ModelScope](https://www.modelscope.cn/models/OpenBMB/MiniCPM5-1B) · BF16 final release (post-trained with RL + OPD) **👈 you are here**
60
+ - **[MiniCPM5-1B-SFT](https://huggingface.co/openbmb/MiniCPM5-1B-SFT)** · [ModelScope](https://www.modelscope.cn/models/OpenBMB/MiniCPM5-1B-SFT) · BF16 SFT-only checkpoint (before RL / OPD)
61
+ - **[MiniCPM5-1B-Base](https://huggingface.co/openbmb/MiniCPM5-1B-Base)** · [ModelScope](https://www.modelscope.cn/models/OpenBMB/MiniCPM5-1B-Base) · BF16 base checkpoint (pre-training only)
62
+ - **[MiniCPM5-1B-GGUF](https://huggingface.co/openbmb/MiniCPM5-1B-GGUF)** · [ModelScope](https://www.modelscope.cn/models/OpenBMB/MiniCPM5-1B-GGUF) · GGUF for llama.cpp / Ollama / LM Studio
63
+ - **[MiniCPM5-1B-MLX](https://huggingface.co/openbmb/MiniCPM5-1B-MLX)** · [ModelScope](https://www.modelscope.cn/models/OpenBMB/MiniCPM5-1B-MLX) · MLX / 4bit for Apple Silicon
64
+
65
+ ## Model Information
66
+
67
+ MiniCPM5-1B has the following features:
68
+
69
+ - **Type**: Causal Language Model
70
+ - **Architecture**: Standard `LlamaForCausalLM`
71
+ - **Number of Parameters**: 1,080,632,832
72
+ - **Number of Non-Embedding Parameters**: 679,552,512
73
+ - **Number of Layers**: 24
74
+ - **Number of Attention Heads (GQA)**: 16 for Q and 2 for KV
75
+ - **Context Length**: 131,072
76
+
77
+ ## Introduction
78
+
79
+ MiniCPM5-1B is the first checkpoint in the MiniCPM5 series. It is designed for local assistants, coding agents, tool-use workflows, and reasoning scenarios where a compact model is preferred. The model keeps a small deployment footprint while providing native long-context support and both Think / No Think chat modes through the same checkpoint.
80
+
81
+ ## Evaluation Results
82
+
83
+ We compare MiniCPM5-1B with strong open-source models in the same size class, including **LFM2.5-1.2B-Thinking**, **Qwen3-0.6B/think** and **Qwen3.5-0.8B/think**. These are capable baselines; within this comparison set, MiniCPM5-1B reaches 1B-class open-source SOTA, with its advantage most visible in tool use, code generation, and difficult reasoning. This makes it a practical choice for local coding agents, tool assistants, and reasoning assistants.
84
+
85
+ ![MiniCPM-5 1B Public Leaderboard](https://raw.githubusercontent.com/OpenBMB/MiniCPM/main/assets/minicpm5/public_leaderboard_en.png)
86
+
87
+ ## Training Recipe
88
+
89
+ The training of MiniCPM5-1B is a full-stack practice of **[UltraData Tiered Data Management](https://arxiv.org/pdf/2602.09003)**, covering three stages: base training, mid-training, and post-training.
90
+
91
+ During **base training**, the model goes through stable training and decay training to build core language capability and training stability. It then enters **mid-training** to further strengthen target capabilities and adapt to the target data distribution. The training corpus is released alongside the model as [Ultra-FineWeb](https://huggingface.co/datasets/openbmb/Ultra-FineWeb), [Ultra-FineWeb-L3](https://huggingface.co/datasets/openbmb/Ultra-FineWeb-L3), and [UltraData-Math](https://huggingface.co/datasets/openbmb/UltraData-Math).
92
+
93
+ During **post-training**, we proceed in three steps: **SFT**, **RL**, and **OPD**. We first use **200B tokens of deep-thinking SFT** and **200B tokens of hybrid-thinking SFT** to establish deep-thinking, hybrid-thinking, and general chat abilities; the SFT data is released as [UltraData-SFT-2605](https://huggingface.co/datasets/openbmb/UltraData-SFT-2605). We then train specialized **RL teachers** for math, code, closed-book QA, writing, and related domains, and use **On-Policy Distillation (OPD)** to distill these teachers back into one release model.
94
+
95
+ ![MiniCPM5-1B Training Recipe](https://raw.githubusercontent.com/OpenBMB/MiniCPM/main/assets/minicpm5/training_recipe.png)
96
+
97
+ ### What does RL + OPD bring?
98
+
99
+ **RL + OPD** is a key part of MiniCPM5-1B post-training. On math, code and instruction-following tasks, RL + OPD raises the average score by **↑16 points** while cutting the share of responses that hit the max-tokens budget by **↓29 percentage points**. The figures below show the two-stage Reasoning RL pipeline, score gains, and the drop in overlong responses.
100
+
101
+ **RL** combines complementary training signals for reasoning, closed-book QA, writing, instruction following, long-context understanding, and general dialogue. Reasoning RL is based on [DAPO-Math-17k](https://huggingface.co/datasets/BytedTsinghua-SIA/DAPO-Math-17k) (inspired by [JustRL](https://arxiv.org/pdf/2512.16649)'s minimalist recipe) and uses a two-stage length schedule to reduce overlong responses while improving reasoning accuracy. We also use [TriviaQA](https://huggingface.co/datasets/mandarjoshi/trivia_qa), [NQ-Open](https://huggingface.co/datasets/google-research-datasets/nq_open), [LongWriter-Zero-RLData](https://huggingface.co/datasets/THU-KEG/LongWriter-Zero-RLData), synthesized verifiable RLVR data, and pair-wise RLHF signals to improve reliability, instruction following, and user experience.
102
+
103
+ ![MiniCPM5-1B RL Two-stage Pipeline](https://raw.githubusercontent.com/OpenBMB/MiniCPM/main/assets/minicpm5/rl_two_stage_overview.png)
104
+
105
+ **OPD** builds on Thinking Machines Lab's [On-Policy Distillation](https://thinkingmachines.ai/blog/on-policy-distillation/) and incorporates implementation improvements from [Rethinking On-Policy Distillation](https://arxiv.org/pdf/2604.13016). In the RL framework, we use reverse KL divergence as the advantage estimate, replacing the original verification-based advantage. At each response position, we take top-k logits from both the student and teacher models, compute reverse KL on the union of the two token sets, and balance the accuracy of the RKL signal with training efficiency. OPD reuses the in-domain prompts used to train each RL teacher as distillation data, so no additional data curation is required.
106
+
107
+ ![MiniCPM5-1B RL + OPD Gains](https://raw.githubusercontent.com/OpenBMB/MiniCPM/main/assets/minicpm5/rl_gains.png)
108
+
109
+ ![MiniCPM5-1B RL + OPD Overlong Response Rate Drop](https://raw.githubusercontent.com/OpenBMB/MiniCPM/main/assets/minicpm5/rl_overlong.png)
110
+
111
+ ## Quickstart
112
+
113
+ ### vLLM
114
+
115
+ ```bash
116
+ pip install "vllm>=0.21"
117
+ vllm serve openbmb/MiniCPM5-1B --port 8000
118
+ ```
119
+
120
+ ```bash
121
+ curl http://localhost:8000/v1/chat/completions \
122
+ -H "Content-Type: application/json" \
123
+ -d '{
124
+ "model": "openbmb/MiniCPM5-1B",
125
+ "messages": [{"role": "user", "content": "Who are you? Please briefly introduce yourself."}],
126
+ "max_tokens": 128,
127
+ "temperature": 0.7
128
+ }'
129
+ ```
130
+
131
+ ### SGLang
132
+
133
+ ```bash
134
+ pip install "sglang[srt]>=0.5.12"
135
+ python -m sglang.launch_server --model-path openbmb/MiniCPM5-1B --port 30000
136
+ ```
137
+
138
+ ```bash
139
+ curl http://localhost:30000/v1/chat/completions \
140
+ -H "Content-Type: application/json" \
141
+ -d '{
142
+ "model": "openbmb/MiniCPM5-1B",
143
+ "messages": [{"role": "user", "content": "Who are you? Please briefly introduce yourself."}],
144
+ "max_tokens": 128,
145
+ "temperature": 0.7
146
+ }'
147
+ ```
148
+
149
+ ### Transformers
150
+
151
+ ```bash
152
+ pip install -U "transformers>=5.6" accelerate torch
153
+ ```
154
+
155
+ ```python
156
+ from transformers import AutoModelForCausalLM, AutoTokenizer
157
+
158
+ model_id = "openbmb/MiniCPM5-1B"
159
+ tokenizer = AutoTokenizer.from_pretrained(model_id)
160
+ model = AutoModelForCausalLM.from_pretrained(
161
+ model_id,
162
+ torch_dtype="auto",
163
+ device_map="auto",
164
+ )
165
+
166
+ messages = [{"role": "user", "content": "Who are you? Please briefly introduce yourself."}]
167
+ inputs = tokenizer.apply_chat_template(
168
+ messages,
169
+ tokenize=True,
170
+ add_generation_prompt=True,
171
+ enable_thinking=False,
172
+ return_dict=True,
173
+ return_tensors="pt",
174
+ ).to(model.device)
175
+
176
+ outputs = model.generate(**inputs, max_new_tokens=128)
177
+ print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
178
+ ```
179
+
180
+ Recommended chat template sampling:
181
+
182
+ | Mode | Recommended params | Enable |
183
+ | --- | --- | --- |
184
+ | **Think** | `temperature=0.9, top_p=0.95` | `enable_thinking=True` |
185
+ | **No Think** | `temperature=0.7, top_p=0.95` | `enable_thinking=False` |
186
+
187
+ ## Tool Calling
188
+
189
+ For tool / function calling, **SGLang is the recommended backend**. MiniCPM5-1B emits XML-style tool calls and SGLang's built-in `minicpm5` parser converts them to OpenAI-compatible `tool_calls` natively:
190
+
191
+ ```bash
192
+ python -m sglang.launch_server --model-path openbmb/MiniCPM5-1B --port 30000 \
193
+ --tool-call-parser minicpm5 # or: --tool-call-parser auto
194
+ ```
195
+
196
+ ## GitHub Cookbooks and Agent Skills
197
+
198
+ MiniCPM5-1B uses the **standard `LlamaForCausalLM` architecture**, so mainstream inference engines can load it directly: **no custom kernels, no model-code fork**. For step-by-step deployment and fine-tuning instructions, use the GitHub cookbooks below. Agent Skills are linked as GitHub resources for users working with Cursor / Claude Code style coding agents.
199
+
200
+ ### Deployment
201
+
202
+ | Backend | Model format / use case | Cookbook | Agent Skill |
203
+ | --- | --- | --- | --- |
204
+ | Transformers | BF16 / FP16 local Python inference, GPU + CPU | [transformers.md](https://github.com/OpenBMB/MiniCPM/blob/main/docs/deployment/transformers.md) | [minicpm5-deploy-transformers](https://github.com/OpenBMB/MiniCPM/blob/main/skills/minicpm5-deploy-transformers/SKILL.md) |
205
+ | vLLM | BF16 / FP16 OpenAI server | [vllm.md](https://github.com/OpenBMB/MiniCPM/blob/main/docs/deployment/vllm.md) | [minicpm5-deploy-vllm](https://github.com/OpenBMB/MiniCPM/blob/main/skills/minicpm5-deploy-vllm/SKILL.md) |
206
+ | SGLang | BF16 / FP16 OpenAI server, recommended for tool calling | [sglang.md](https://github.com/OpenBMB/MiniCPM/blob/main/docs/deployment/sglang.md) | [minicpm5-deploy-sglang](https://github.com/OpenBMB/MiniCPM/blob/main/skills/minicpm5-deploy-sglang/SKILL.md) |
207
+ | llama.cpp | GGUF local inference, CPU/GPU | [llama_cpp.md](https://github.com/OpenBMB/MiniCPM/blob/main/docs/deployment/llama_cpp.md) | [minicpm5-deploy-llama-cpp](https://github.com/OpenBMB/MiniCPM/blob/main/skills/minicpm5-deploy-llama-cpp/SKILL.md) |
208
+ | Ollama | GGUF local on-device runtime | [ollama.md](https://github.com/OpenBMB/MiniCPM/blob/main/docs/deployment/ollama.md) | [minicpm5-deploy-ollama](https://github.com/OpenBMB/MiniCPM/blob/main/skills/minicpm5-deploy-ollama/SKILL.md) |
209
+ | LM Studio | GGUF Mac desktop app and OpenAI server | [lmstudio.md](https://github.com/OpenBMB/MiniCPM/blob/main/docs/deployment/lmstudio.md) | [minicpm5-deploy-lmstudio](https://github.com/OpenBMB/MiniCPM/blob/main/skills/minicpm5-deploy-lmstudio/SKILL.md) |
210
+ | MLX | MLX / 4bit local inference on Apple Silicon | [mlx.md](https://github.com/OpenBMB/MiniCPM/blob/main/docs/deployment/mlx.md) | [minicpm5-deploy-mlx](https://github.com/OpenBMB/MiniCPM/blob/main/skills/minicpm5-deploy-mlx/SKILL.md) |
211
+ | ArcLight | GGUF local on-device, CPU, Desktop & Server | [arclight.md](https://github.com/OpenBMB/MiniCPM/blob/main/docs/deployment/arclight.md) | [minicpm5-deploy-arclight](https://github.com/OpenBMB/MiniCPM/blob/main/skills/minicpm5-deploy-arclight/SKILL.md) |
212
+
213
+ ### Fine-tuning
214
+
215
+ | Framework | Use case | Cookbook | Agent Skill |
216
+ | --- | --- | --- | --- |
217
+ | TRL + PEFT | LoRA / SFT fine-tuning | [trl.md](https://github.com/OpenBMB/MiniCPM/blob/main/docs/finetune/trl.md) | [minicpm5-finetune-trl](https://github.com/OpenBMB/MiniCPM/blob/main/skills/minicpm5-finetune-trl/SKILL.md) |
218
+ | LLaMA-Factory | Fine-tuning | [llamafactory.md](https://github.com/OpenBMB/MiniCPM/blob/main/docs/finetune/llamafactory.md) | [minicpm5-finetune-llamafactory](https://github.com/OpenBMB/MiniCPM/blob/main/skills/minicpm5-finetune-llamafactory/SKILL.md) |
219
+ | ms-swift | Fine-tuning | [ms_swift.md](https://github.com/OpenBMB/MiniCPM/blob/main/docs/finetune/ms_swift.md) | [minicpm5-finetune-ms-swift](https://github.com/OpenBMB/MiniCPM/blob/main/skills/minicpm5-finetune-ms-swift/SKILL.md) |
220
+ | unsloth | Fine-tuning | [unsloth.md](https://github.com/OpenBMB/MiniCPM/blob/main/docs/finetune/unsloth.md) | [minicpm5-finetune-unsloth](https://github.com/OpenBMB/MiniCPM/blob/main/skills/minicpm5-finetune-unsloth/SKILL.md) |
221
+ | xtuner | Fine-tuning | [xtuner.md](https://github.com/OpenBMB/MiniCPM/blob/main/docs/finetune/xtuner.md) | [minicpm5-finetune-xtuner](https://github.com/OpenBMB/MiniCPM/blob/main/skills/minicpm5-finetune-xtuner/SKILL.md) |
222
+
223
+ ### Other Supported Frameworks
224
+
225
+ In addition to the deployment and fine-tuning frameworks listed above, MiniCPM5-1B is also supported by FlagOS for multi-chip deployment.
226
+
227
+ #### FlagOS Overview
228
+
229
+ To enable large-scale deployment across different AI chips, Beijing Zhiyuan Research Institute, together with numerous research institutions, chip manufacturers, system vendors, and algorithm and software organizations both domestically and internationally, jointly initiated and established the FlagOS Open Source Community.
230
+
231
+ The FlagOS community is dedicated to building a unified, open-source system software stack for various AI chips, encompassing core open-source projects such as a large-scale operator library, a unified AI compiler, parallel training and inference frameworks, and a unified communication library. It aims to create an open technology ecosystem connecting the “model-system-chip” layers. By enabling “develop once, deploy across chips”, FlagOS unlocks the computational potential of hardware, breaks down the ecosystem silos between different chip software stacks, and effectively reduces migration costs for developers.The FlagOS community fosters an AI hardware and software ecosystem, overcomes single-vendor closed-source monopolies, promotes widespread deployment of AI hardware technologies, and is committed to rooted in China while embracing global collaboration.
232
+
233
+ Official website express: [https://flagos.io](https://flagos.io/)
234
+
235
+ <details>
236
+ <summary>FlagOS multi-chip support and usage</summary>
237
+
238
+ #### FlagOS: Supporting Multiple AI Chips
239
+
240
+ Thanks to FlagOS’s unified multi-chip AI system software stack, MiniCPM5-1B was adapted to 4–5 different AI chips in an extremely short time. Currently, the multi-chip version of MiniCPM5-1B has been released on FlagRelease, FlagOS’s platform for automatic migration, adaptation, and deployment of large models across multi-architecture AI chips. Details are as follows:
241
+
242
+ |Vendor|ModelScope|Huggingface|
243
+ |---|---|---|
244
+ |Nvidia|[MiniCPM5-1B-nvidia-FlagOS](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-nvidia-FlagOS)|[MiniCPM5-1B-nvidia-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-nvidia-FlagOS)|
245
+ |Hygon|[MiniCPM5-1B-hygon-FlagOS](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-hygon-FlagOS)|[MiniCPM5-1B-hygon-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-hygon-FlagOS)|
246
+ |Metax|[MiniCPM5-1B-metax-FlagOS](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-metax-FlagOS)|[MiniCPM5-1B-metax-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-metax-FlagOS)|
247
+ |Iluvatar|[MiniCPM5-1B-iluvatar-FlagOS](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-iluvatar-FlagOS)|[MiniCPM5-1B-iluvatar-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-iluvatar-FlagOS)|
248
+ |Zhenwu|[MiniCPM5-1B-zhenwu-FlagOS](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-zhenwu-FlagOS)|[MiniCPM5-1B-zhenwu-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-zhenwu-FlagOS)|
249
+ |Mthreads|[MiniCPM5-1B-mthreads-FlagOS](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-mthreads-FlagOS)|[MiniCPM5-1B-mthreads-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-mthreads-FlagOS)|
250
+ |Kunlunxin|[MiniCPM5-1B-kunlunxin-FlagOS](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-kunlunxin-FlagOS)|[MiniCPM5-1B-kunlunxin-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-kunlunxin-FlagOS)|
251
+ |Ascend|[MiniCPM5-1B-ascend-FlagOS](https://modelscope.cn/models/FlagRelease/MiniCPM5-1B-ascend-FlagOS)|[MiniCPM5-1B-ascend-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-ascend-FlagOS)|
252
+ |ARM-v9|[MiniCPM5-1B-Armv9-FlagOS](https://modelscope.cn/models/FlagRelease/MiniCPM5-1B-Armv9-FlagOS)|[MiniCPM5-1B-Armv9-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-Armv9-FlagOS)|
253
+
254
+ #### FlagOS Usage
255
+
256
+ ##### FlagOS Performance Acceleration on Nvidia
257
+
258
+ ###### From FlagRelease (**Recommendation**)
259
+
260
+ FlagRelease is a platform developed by the FlagOS team for automatic migration, adaptation, and deployment of large models across multi-architecture AI chips. The multi-chip version of MiniCPM5-1B has already been released on FlagRelease. All necessary software packages are pre-installed on the platform, so users do not need to install anything.
261
+
262
+ ###### FlagRelease Image Key Versions
263
+
264
+ ###### FlagRelease Quick Start
265
+
266
+ |Vendor|ModelScope|Huggingface|
267
+ |---|---|---|
268
+ |Nvidia|[MiniCPM5-1B-nvidia-FlagOS](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-nvidia-FlagOS)|[MiniCPM5-1B-nvidia-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-nvidia-FlagOS)|
269
+ |Hygon|[MiniCPM5-1B-hygon-FlagOS](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-hygon-FlagOS)|[MiniCPM5-1B-hygon-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-hygon-FlagOS)|
270
+ |Metax|[MiniCPM5-1B-metax-FlagOS](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-metax-FlagOS)|[MiniCPM5-1B-metax-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-metax-FlagOS)|
271
+ |Iluvatar|[MiniCPM5-1B-iluvatar-FlagOS](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-iluvatar-FlagOS)|[MiniCPM5-1B-iluvatar-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-iluvatar-FlagOS)|
272
+ |Zhenwu|[MiniCPM5-1B-zhenwu-FlagOS](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-zhenwu-FlagOS)|[MiniCPM5-1B-zhenwu-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-zhenwu-FlagOS)|
273
+ |Mthreads|[MiniCPM5-1B-mthreads-FlagOS](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-mthreads-FlagOS)|[MiniCPM5-1B-mthreads-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-mthreads-FlagOS)|
274
+ |Kunlunxin|[MiniCPM5-1B-kunlunxin-FlagOS](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-kunlunxin-FlagOS)|[MiniCPM5-1B-kunlunxin-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-kunlunxin-FlagOS)|
275
+ |Ascend|[MiniCPM5-1B-ascend-FlagOS](https://modelscope.cn/models/FlagRelease/MiniCPM5-1B-ascend-FlagOS)|[MiniCPM5-1B-ascend-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-ascend-FlagOS)|
276
+ |ARM-v9|[MiniCPM5-1B-Armv9-FlagOS](https://modelscope.cn/models/FlagRelease/MiniCPM5-1B-Armv9-FlagOS)|[MiniCPM5-1B-Armv9-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-Armv9-FlagOS)|
277
+
278
+ ###### From Scratch
279
+
280
+ - Dependencies: Python 3.12, GLIBC 2.39, GLIBCXX 3.4.33, CXXABI 1.3.15
281
+
282
+ ###### Vllm Version
283
+
284
+ ###### Installing the FlagOS Operator Library
285
+
286
+ Official Repository: https://github.com/flagos-ai/FlagGems
287
+
288
+ ```PowerShell
289
+ pip install flag-gems==4.2.1rc0
290
+ pip install triton==3.5.1
291
+ ```
292
+
293
+ ###### Activating Acceleration
294
+
295
+ You can enable flagGems acceleration by adding the import of flagGems in the source code of vllm where inference is performed.
296
+
297
+ ```Bash
298
+ import flag_gems
299
+ flag_gems.enable(record=True, once=True, path="/root/gems.txt")
300
+ ```
301
+
302
+ ```PowerShell
303
+ vllm serve ${model_path} \
304
+ --trust-remote-code \
305
+ --dtype bfloat16 \
306
+ --enforce-eager \
307
+ --port ${Port} \
308
+ --served-model-name ${model_name} \
309
+ --gpu-memory-utilization 0.85
310
+ ```
311
+
312
+ ##### Using FlagOS Unified Multi-Chip Backend Plugin
313
+
314
+ [**vllm-plugin-FL**](https://github.com/flagos-ai/vllm-plugin-FL) is a plugin built for the vLLM inference/service framework. Developed on top of FlagOS’s unified multi-chip backend, it is designed to extend vLLM’s capabilities and performance across a variety of hardware environments.
315
+
316
+ ###### Using vllm-plugin-FL
317
+
318
+ |Vendor|From Scratch|From FlagRelease||
319
+ |---|---|---|---|
320
+ |Nvidia|[vllm-plugin-FL/MiniCPM5-1B](https://github.com/flagos-ai/vllm-plugin-FL/blob/main/examples/minicpm/README.md)|[MiniCPM5-1B-ModelScope](https://www.modelscope.cn/models/FlagRelease/MiniCPM5-1B-nvidia-FlagOS)|[MiniCPM5-1B-nvidia-FlagOS](https://huggingface.co/FlagRelease/MiniCPM5-1B-nvidia-FlagOS)|
321
+
322
+ </details>
323
+
324
+ ## Desktop Pet
325
+
326
+ We also ship **[OpenBMB/MiniCPM-Desk-Pet](https://github.com/OpenBMB/MiniCPM-Desk-Pet)**, a desktop pet driven locally by MiniCPM5-1B. It supports Apple Silicon / NVIDIA GPU / CPU paths, can work with coding agents such as Cursor, Claude Code, and Codex, and supports LoRA persona switching.
327
+
328
+ <a href="https://youtu.be/Ee0slMW8SEk"><img src="https://img.youtube.com/vi/Ee0slMW8SEk/0.jpg" alt="MiniCPM Desk Pet video demo" width="720"></a>
329
+
330
+ ## Limitations and Responsible Use
331
+
332
+ MiniCPM5-1B is a language model that generates content based on learned statistical patterns from training data. It may produce inaccurate, biased, or unsafe outputs, and generated content should be reviewed and verified before use in high-stakes settings.
333
+
334
+ Users are responsible for evaluating outputs, applying appropriate safeguards, and complying with applicable laws, regulations, and platform policies.
335
+
336
+ ## License
337
+
338
+ This repository and MiniCPM model weights are released under the [Apache-2.0](https://github.com/OpenBMB/MiniCPM/blob/main/LICENSE) License.
339
+
340
+ ## Citation
341
+
342
+ Please cite our paper if you find our work valuable:
343
+
344
+ ```bibtex
345
+ @article{minicpm4,
346
+ title={Minicpm4: Ultra-efficient llms on end devices},
347
+ author={MiniCPM, Team},
348
+ journal={arXiv preprint arXiv:2506.07900},
349
+ year={2025}
350
+ }
351
+ ```
chat_template.jinja ADDED
@@ -0,0 +1,179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token }}{%- if tools %}
2
+ {%- set tool_definitions %}
3
+ {{- "# Tools\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
4
+ {%- for tool in tools %}
5
+ {{- "\n" }}
6
+ {{- tool | tojson(ensure_ascii=False) }}
7
+ {%- endfor %}
8
+ {{- '\n</tools>\n\nTool usage guidelines:\n- You may call zero or more functions. If no function calls are needed, just answer normally and do not include any <function ... </function>.\n- When calling a function, return an XML object within <function ... </function> using:\n<function name="function-name"><param name="param-name">param-value</param></function>\n- param-value may be multi-line. If it contains <, & or newline characters, wrap it in a CDATA block: <param name="param-name"><![CDATA[...multi-line value...]]></param>' }}
9
+ {%- endset %}
10
+
11
+ {{- '<|im_start|>system\n' }}
12
+ {%- if messages[0].role == 'system' %}
13
+ {%- if '<tool_def_sep>' in messages[0].content %}
14
+ {{- messages[0].content.replace('<tool_def_sep>', tool_definitions) }}
15
+ {%- else %}
16
+ {{- messages[0].content + '\n\n' + tool_definitions }}
17
+ {%- endif %}
18
+ {%- else %}
19
+ {{- tool_definitions.lstrip() }}
20
+ {%- endif %}
21
+ {{- '<|im_end|>\n' }}
22
+ {%- else %}
23
+ {%- if messages[0].role == 'system' %}
24
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
25
+ {%- endif %}
26
+ {%- endif %}
27
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
28
+ {%- for message in messages[::-1] %}
29
+ {%- set index = (messages|length - 1) - loop.index0 %}
30
+ {%- 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>')) %}
31
+ {%- set ns.multi_step_tool = false %}
32
+ {%- set ns.last_query_index = index %}
33
+ {%- endif %}
34
+ {%- endfor %}
35
+ {%- for message in messages %}
36
+ {%- if message.content is string %}
37
+ {%- set content = message.content %}
38
+ {%- else %}
39
+ {%- set content = '' %}
40
+ {%- endif %}
41
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
42
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
43
+ {%- elif message.role == "assistant" %}
44
+ {%- set reasoning_content = '' %}
45
+ {%- if message.reasoning_content is string %}
46
+ {%- set reasoning_content = message.reasoning_content %}
47
+ {%- else %}
48
+ {%- if '</think>' in content %}
49
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
50
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
51
+ {%- endif %}
52
+ {%- endif %}
53
+
54
+ {%- if message.tool_calls %}
55
+ {%- set content_parts = content.split('<tool_sep>') %}
56
+ {%- set processed_content = content_parts[0] %}
57
+ {%- set tool_calls_count = message.tool_calls|length %}
58
+ {%- set tool_sep_count = content_parts|length - 1 %}
59
+ {%- set min_count = [tool_calls_count, tool_sep_count]|min %}
60
+
61
+ {%- for i in range(1, content_parts|length) %}
62
+ {%- set tool_index = i - 1 %}
63
+ {%- if tool_index < tool_calls_count %}
64
+ {%- set tool_call = message.tool_calls[tool_index] %}
65
+ {%- if tool_call.function %}
66
+ {%- set tool_call = tool_call.function %}
67
+ {%- endif %}
68
+ {%- set single_tool_xml %}
69
+ {{- '<function name="' ~ tool_call.name ~ '">' }}
70
+ {%- if tool_call.arguments %}
71
+ {%- set args_dict = tool_call.arguments %}
72
+ {%- for param_name, param_value in args_dict.items() %}
73
+ {{- '<param name="' ~ param_name ~ '">' }}
74
+ {%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
75
+ {{- '<![CDATA[' + param_value + ']]>' }}
76
+ {%- else %}
77
+ {{- param_value }}
78
+ {%- endif %}
79
+ {{- '</param>' }}
80
+ {%- endfor %}
81
+ {%- endif %}
82
+ {{- '</function>' }}
83
+ {%- endset %}
84
+ {%- set processed_content = processed_content + single_tool_xml + content_parts[i] %}
85
+ {%- else %}
86
+ {%- set processed_content = processed_content + content_parts[i] %}
87
+ {%- endif %}
88
+ {%- endfor %}
89
+
90
+ {%- if tool_calls_count > tool_sep_count %}
91
+ {%- for remaining_index in range(tool_sep_count, tool_calls_count) %}
92
+ {%- set tool_call = message.tool_calls[remaining_index] %}
93
+ {%- if tool_call.function %}
94
+ {%- set tool_call = tool_call.function %}
95
+ {%- endif %}
96
+ {%- set remaining_tool_xml %}
97
+ {{- '<function name="' ~ tool_call.name ~ '">' }}
98
+ {%- if tool_call.arguments %}
99
+ {%- set args_dict = tool_call.arguments %}
100
+ {%- for param_name, param_value in args_dict.items() %}
101
+ {{- '<param name="' ~ param_name ~ '">' }}
102
+ {%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
103
+ {{- '<![CDATA[' + param_value + ']]>' }}
104
+ {%- else %}
105
+ {{- param_value }}
106
+ {%- endif %}
107
+ {{- '</param>' }}
108
+ {%- endfor %}
109
+ {%- endif %}
110
+ {{- '</function>' }}
111
+ {%- endset %}
112
+ {%- set processed_content = processed_content + remaining_tool_xml %}
113
+ {%- endfor %}
114
+ {%- endif %}
115
+
116
+ {%- set content = processed_content %}
117
+ {%- endif %}
118
+
119
+ {%- if loop.index0 > ns.last_query_index %}
120
+ {%- if reasoning_content %}
121
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
122
+ {%- else %}
123
+ {{- '<|im_start|>' + message.role + '\n' + content }}
124
+ {%- endif %}
125
+ {%- else %}
126
+ {{- '<|im_start|>' + message.role + '\n' + content }}
127
+ {%- endif %}
128
+
129
+ {%- if message.tool_calls and not has_tool_sep %}
130
+ {%- for tool_call in message.tool_calls %}
131
+ {%- if (loop.first and content) or (not loop.first) %}
132
+ {{- '\n' }}
133
+ {%- endif %}
134
+ {%- if tool_call.function %}
135
+ {%- set tool_call = tool_call.function %}
136
+ {%- endif %}
137
+ {{- '<function name="' ~ tool_call.name ~ '">' }}
138
+ {%- if tool_call.arguments %}
139
+ {%- set args_dict = tool_call.arguments %}
140
+ {%- for param_name, param_value in args_dict.items() %}
141
+ {{- '<param name="' ~ param_name ~ '">' }}
142
+ {%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
143
+ {{- '<![CDATA[' + param_value + ']]>' }}
144
+ {%- else %}
145
+ {{- param_value }}
146
+ {%- endif %}
147
+ {{- '</param>' }}
148
+ {%- endfor %}
149
+ {%- endif %}
150
+ {{- '</function>' }}
151
+ {%- endfor %}
152
+ {%- endif %}
153
+ {{- '<|im_end|>\n' }}
154
+ {%- elif message.role == "tool" %}
155
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
156
+ {{- '<|im_start|>user' }}
157
+ {%- endif %}
158
+ {{- '\n<tool_response>\n' }}
159
+ {%- if message.content is string %}
160
+ {{- content }}
161
+ {%- else %}
162
+ {{- message.content | tojson(ensure_ascii=False) }}
163
+ {%- endif %}
164
+ {{- '\n</tool_response>' }}
165
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
166
+ {{- '<|im_end|>\n' }}
167
+ {%- endif %}
168
+ {%- endif %}
169
+ {%- endfor %}
170
+ {%- if add_generation_prompt %}
171
+ {{- '<|im_start|>assistant\n' }}
172
+ {%- if enable_thinking is defined %}
173
+ {%- if enable_thinking is false %}
174
+ {{- '<think>\n\n</think>\n\n' }}
175
+ {%- elif enable_thinking is true %}
176
+ {{- '<think>\n' }}
177
+ {%- endif %}
178
+ {%- endif %}
179
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openbmb/MiniCPM5-1B",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "eos_token_id": [
8
+ 1,
9
+ 130073
10
+ ],
11
+ "pad_token_id": 1,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 1536,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 4608,
16
+ "max_position_embeddings": 131072,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
20
+ "num_key_value_heads": 2,
21
+ "head_dim": 128,
22
+ "rms_norm_eps": 1e-06,
23
+ "rope_theta": 5000000,
24
+ "rope_scaling": null,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "5.6.2",
28
+ "use_cache": true,
29
+ "vocab_size": 130560
30
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": [
5
+ 1,
6
+ 130073
7
+ ],
8
+ "pad_token_id": 1,
9
+ "do_sample": true,
10
+ "temperature": 0.9,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.6.2"
13
+ }
model-00000-of-00001.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ab8fd86563125929be78aeec8cb3969c7ed2ead3be1ab9d3ec0a9fa69c8660d
3
+ size 2161290912
model.safetensors.index.json ADDED
@@ -0,0 +1,226 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 2161265664
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00000-of-00001.safetensors",
7
+ "lm_head.weight": "model-00000-of-00001.safetensors",
8
+ "model.layers.0.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
9
+ "model.layers.1.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
10
+ "model.layers.2.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
11
+ "model.layers.3.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
12
+ "model.layers.4.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
13
+ "model.layers.5.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
14
+ "model.layers.6.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
15
+ "model.layers.7.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
16
+ "model.layers.8.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
17
+ "model.layers.9.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
18
+ "model.layers.10.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
19
+ "model.layers.11.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
20
+ "model.layers.12.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
21
+ "model.layers.13.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
22
+ "model.layers.14.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
23
+ "model.layers.15.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
24
+ "model.layers.16.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
25
+ "model.layers.17.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
26
+ "model.layers.18.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
27
+ "model.layers.19.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
28
+ "model.layers.20.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
29
+ "model.layers.21.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
30
+ "model.layers.22.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
31
+ "model.layers.23.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
32
+ "model.layers.0.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
33
+ "model.layers.0.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
34
+ "model.layers.0.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
35
+ "model.layers.1.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
36
+ "model.layers.1.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
37
+ "model.layers.1.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
38
+ "model.layers.2.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
39
+ "model.layers.2.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
40
+ "model.layers.2.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
41
+ "model.layers.3.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
42
+ "model.layers.3.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
43
+ "model.layers.3.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
44
+ "model.layers.4.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
45
+ "model.layers.4.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
46
+ "model.layers.4.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
47
+ "model.layers.5.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
48
+ "model.layers.5.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
49
+ "model.layers.5.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
50
+ "model.layers.6.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
51
+ "model.layers.6.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
52
+ "model.layers.6.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
53
+ "model.layers.7.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
54
+ "model.layers.7.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
55
+ "model.layers.7.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
56
+ "model.layers.8.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
57
+ "model.layers.8.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
58
+ "model.layers.8.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
59
+ "model.layers.9.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
60
+ "model.layers.9.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
61
+ "model.layers.9.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
62
+ "model.layers.10.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
63
+ "model.layers.10.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
64
+ "model.layers.10.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
65
+ "model.layers.11.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
66
+ "model.layers.11.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
67
+ "model.layers.11.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
68
+ "model.layers.12.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
69
+ "model.layers.12.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
70
+ "model.layers.12.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
71
+ "model.layers.13.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
72
+ "model.layers.13.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
73
+ "model.layers.13.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
74
+ "model.layers.14.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
75
+ "model.layers.14.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
76
+ "model.layers.14.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
77
+ "model.layers.15.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
78
+ "model.layers.15.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
80
+ "model.layers.16.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
81
+ "model.layers.16.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
82
+ "model.layers.16.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
83
+ "model.layers.17.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
84
+ "model.layers.17.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
85
+ "model.layers.17.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
86
+ "model.layers.18.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
87
+ "model.layers.18.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
88
+ "model.layers.18.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
89
+ "model.layers.19.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
90
+ "model.layers.19.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
91
+ "model.layers.19.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
92
+ "model.layers.20.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
93
+ "model.layers.20.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
94
+ "model.layers.20.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
95
+ "model.layers.21.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
96
+ "model.layers.21.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
97
+ "model.layers.21.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
98
+ "model.layers.22.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
99
+ "model.layers.22.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
100
+ "model.layers.22.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
101
+ "model.layers.23.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
102
+ "model.layers.23.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
103
+ "model.layers.23.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
104
+ "model.layers.0.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
105
+ "model.layers.0.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
106
+ "model.layers.1.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
107
+ "model.layers.1.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
108
+ "model.layers.2.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
109
+ "model.layers.2.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
110
+ "model.layers.3.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
111
+ "model.layers.3.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
112
+ "model.layers.4.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
113
+ "model.layers.4.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
114
+ "model.layers.5.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
115
+ "model.layers.5.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
116
+ "model.layers.6.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
117
+ "model.layers.6.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
118
+ "model.layers.7.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
119
+ "model.layers.7.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
120
+ "model.layers.8.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
121
+ "model.layers.8.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
122
+ "model.layers.9.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
123
+ "model.layers.9.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
124
+ "model.layers.10.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
125
+ "model.layers.10.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
126
+ "model.layers.11.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
127
+ "model.layers.11.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
128
+ "model.layers.12.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
129
+ "model.layers.12.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
130
+ "model.layers.13.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
131
+ "model.layers.13.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
132
+ "model.layers.14.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
133
+ "model.layers.14.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
134
+ "model.layers.15.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
135
+ "model.layers.15.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
136
+ "model.layers.16.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
137
+ "model.layers.16.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
138
+ "model.layers.17.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
139
+ "model.layers.17.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
140
+ "model.layers.18.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
141
+ "model.layers.18.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
144
+ "model.layers.20.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
145
+ "model.layers.20.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
146
+ "model.layers.21.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
147
+ "model.layers.21.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
148
+ "model.layers.22.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
149
+ "model.layers.22.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
150
+ "model.layers.23.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
151
+ "model.layers.23.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
152
+ "model.layers.0.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
153
+ "model.layers.1.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
154
+ "model.layers.2.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
155
+ "model.layers.3.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
156
+ "model.layers.4.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
157
+ "model.layers.5.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
158
+ "model.layers.6.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
159
+ "model.layers.7.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
160
+ "model.layers.8.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
161
+ "model.layers.9.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
162
+ "model.layers.10.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
163
+ "model.layers.11.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
164
+ "model.layers.12.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
165
+ "model.layers.13.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
166
+ "model.layers.14.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
167
+ "model.layers.15.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
168
+ "model.layers.16.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
169
+ "model.layers.17.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
170
+ "model.layers.18.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
171
+ "model.layers.19.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
172
+ "model.layers.20.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
173
+ "model.layers.21.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
174
+ "model.layers.22.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
175
+ "model.layers.23.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
176
+ "model.layers.0.input_layernorm.weight": "model-00000-of-00001.safetensors",
177
+ "model.layers.1.input_layernorm.weight": "model-00000-of-00001.safetensors",
178
+ "model.layers.2.input_layernorm.weight": "model-00000-of-00001.safetensors",
179
+ "model.layers.3.input_layernorm.weight": "model-00000-of-00001.safetensors",
180
+ "model.layers.4.input_layernorm.weight": "model-00000-of-00001.safetensors",
181
+ "model.layers.5.input_layernorm.weight": "model-00000-of-00001.safetensors",
182
+ "model.layers.6.input_layernorm.weight": "model-00000-of-00001.safetensors",
183
+ "model.layers.7.input_layernorm.weight": "model-00000-of-00001.safetensors",
184
+ "model.layers.8.input_layernorm.weight": "model-00000-of-00001.safetensors",
185
+ "model.layers.9.input_layernorm.weight": "model-00000-of-00001.safetensors",
186
+ "model.layers.10.input_layernorm.weight": "model-00000-of-00001.safetensors",
187
+ "model.layers.11.input_layernorm.weight": "model-00000-of-00001.safetensors",
188
+ "model.layers.12.input_layernorm.weight": "model-00000-of-00001.safetensors",
189
+ "model.layers.13.input_layernorm.weight": "model-00000-of-00001.safetensors",
190
+ "model.layers.14.input_layernorm.weight": "model-00000-of-00001.safetensors",
191
+ "model.layers.15.input_layernorm.weight": "model-00000-of-00001.safetensors",
192
+ "model.layers.16.input_layernorm.weight": "model-00000-of-00001.safetensors",
193
+ "model.layers.17.input_layernorm.weight": "model-00000-of-00001.safetensors",
194
+ "model.layers.18.input_layernorm.weight": "model-00000-of-00001.safetensors",
195
+ "model.layers.19.input_layernorm.weight": "model-00000-of-00001.safetensors",
196
+ "model.layers.20.input_layernorm.weight": "model-00000-of-00001.safetensors",
197
+ "model.layers.21.input_layernorm.weight": "model-00000-of-00001.safetensors",
198
+ "model.layers.22.input_layernorm.weight": "model-00000-of-00001.safetensors",
199
+ "model.layers.23.input_layernorm.weight": "model-00000-of-00001.safetensors",
200
+ "model.layers.0.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
201
+ "model.layers.1.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
202
+ "model.layers.2.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
203
+ "model.layers.3.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
204
+ "model.layers.4.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
205
+ "model.layers.5.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
206
+ "model.layers.6.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
207
+ "model.layers.7.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
208
+ "model.layers.8.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
209
+ "model.layers.9.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
210
+ "model.layers.10.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
211
+ "model.layers.11.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
212
+ "model.layers.12.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
213
+ "model.layers.13.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
214
+ "model.layers.14.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
215
+ "model.layers.15.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
216
+ "model.layers.16.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
217
+ "model.layers.17.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
218
+ "model.layers.18.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
219
+ "model.layers.19.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
220
+ "model.layers.20.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
221
+ "model.layers.21.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
222
+ "model.layers.22.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
223
+ "model.layers.23.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
224
+ "model.norm.weight": "model-00000-of-00001.safetensors"
225
+ }
226
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,4099 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<s>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "<tool_call>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "3": {
31
+ "content": "</tool_call>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "4": {
39
+ "content": "<|im_sep|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "5": {
47
+ "content": "<|fim_prefix|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "6": {
55
+ "content": "<|fim_middle|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "7": {
63
+ "content": "<|fim_suffix|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "8": {
71
+ "content": "<think>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "9": {
79
+ "content": "</think>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "10": {
87
+ "content": "<tool_response>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "11": {
95
+ "content": "</tool_response>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "12": {
103
+ "content": "<tools>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "13": {
111
+ "content": "</tools>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "14": {
119
+ "content": "<arguments>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": true
125
+ },
126
+ "15": {
127
+ "content": "</arguments>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": true
133
+ },
134
+ "16": {
135
+ "content": "<parameters>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": true
141
+ },
142
+ "17": {
143
+ "content": "</parameters>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": true
149
+ },
150
+ "18": {
151
+ "content": "<function",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": true
157
+ },
158
+ "19": {
159
+ "content": "</function>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": true
165
+ },
166
+ "20": {
167
+ "content": "<param",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": true
173
+ },
174
+ "21": {
175
+ "content": "</param>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": true
181
+ },
182
+ "130072": {
183
+ "content": "<|im_start|>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": true
189
+ },
190
+ "130073": {
191
+ "content": "<|im_end|>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": true
197
+ },
198
+ "130074": {
199
+ "content": "<unk>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": true
205
+ },
206
+ "130075": {
207
+ "content": "<|thought_begin|>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": true
213
+ },
214
+ "130076": {
215
+ "content": "<|thought_end|>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": true
221
+ },
222
+ "130077": {
223
+ "content": "<|tool_call|>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": true
229
+ },
230
+ "130078": {
231
+ "content": "<|execute_start|>",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": true
237
+ },
238
+ "130079": {
239
+ "content": "<|execute_end|>",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": false,
243
+ "single_word": false,
244
+ "special": true
245
+ },
246
+ "130080": {
247
+ "content": "/think",
248
+ "lstrip": false,
249
+ "normalized": false,
250
+ "rstrip": false,
251
+ "single_word": false,
252
+ "special": true
253
+ },
254
+ "130081": {
255
+ "content": "/no_think",
256
+ "lstrip": false,
257
+ "normalized": false,
258
+ "rstrip": false,
259
+ "single_word": false,
260
+ "special": true
261
+ },
262
+ "130082": {
263
+ "content": "<unused_token_0>",
264
+ "lstrip": false,
265
+ "normalized": true,
266
+ "rstrip": false,
267
+ "single_word": false,
268
+ "special": false
269
+ },
270
+ "130083": {
271
+ "content": "<unused_token_1>",
272
+ "lstrip": false,
273
+ "normalized": true,
274
+ "rstrip": false,
275
+ "single_word": false,
276
+ "special": false
277
+ },
278
+ "130084": {
279
+ "content": "<unused_token_2>",
280
+ "lstrip": false,
281
+ "normalized": true,
282
+ "rstrip": false,
283
+ "single_word": false,
284
+ "special": false
285
+ },
286
+ "130085": {
287
+ "content": "<unused_token_3>",
288
+ "lstrip": false,
289
+ "normalized": true,
290
+ "rstrip": false,
291
+ "single_word": false,
292
+ "special": false
293
+ },
294
+ "130086": {
295
+ "content": "<unused_token_4>",
296
+ "lstrip": false,
297
+ "normalized": true,
298
+ "rstrip": false,
299
+ "single_word": false,
300
+ "special": false
301
+ },
302
+ "130087": {
303
+ "content": "<unused_token_5>",
304
+ "lstrip": false,
305
+ "normalized": true,
306
+ "rstrip": false,
307
+ "single_word": false,
308
+ "special": false
309
+ },
310
+ "130088": {
311
+ "content": "<unused_token_6>",
312
+ "lstrip": false,
313
+ "normalized": true,
314
+ "rstrip": false,
315
+ "single_word": false,
316
+ "special": false
317
+ },
318
+ "130089": {
319
+ "content": "<unused_token_7>",
320
+ "lstrip": false,
321
+ "normalized": true,
322
+ "rstrip": false,
323
+ "single_word": false,
324
+ "special": false
325
+ },
326
+ "130090": {
327
+ "content": "<unused_token_8>",
328
+ "lstrip": false,
329
+ "normalized": true,
330
+ "rstrip": false,
331
+ "single_word": false,
332
+ "special": false
333
+ },
334
+ "130091": {
335
+ "content": "<unused_token_9>",
336
+ "lstrip": false,
337
+ "normalized": true,
338
+ "rstrip": false,
339
+ "single_word": false,
340
+ "special": false
341
+ },
342
+ "130092": {
343
+ "content": "<unused_token_10>",
344
+ "lstrip": false,
345
+ "normalized": true,
346
+ "rstrip": false,
347
+ "single_word": false,
348
+ "special": false
349
+ },
350
+ "130093": {
351
+ "content": "<unused_token_11>",
352
+ "lstrip": false,
353
+ "normalized": true,
354
+ "rstrip": false,
355
+ "single_word": false,
356
+ "special": false
357
+ },
358
+ "130094": {
359
+ "content": "<unused_token_12>",
360
+ "lstrip": false,
361
+ "normalized": true,
362
+ "rstrip": false,
363
+ "single_word": false,
364
+ "special": false
365
+ },
366
+ "130095": {
367
+ "content": "<unused_token_13>",
368
+ "lstrip": false,
369
+ "normalized": true,
370
+ "rstrip": false,
371
+ "single_word": false,
372
+ "special": false
373
+ },
374
+ "130096": {
375
+ "content": "<unused_token_14>",
376
+ "lstrip": false,
377
+ "normalized": true,
378
+ "rstrip": false,
379
+ "single_word": false,
380
+ "special": false
381
+ },
382
+ "130097": {
383
+ "content": "<unused_token_15>",
384
+ "lstrip": false,
385
+ "normalized": true,
386
+ "rstrip": false,
387
+ "single_word": false,
388
+ "special": false
389
+ },
390
+ "130098": {
391
+ "content": "<unused_token_16>",
392
+ "lstrip": false,
393
+ "normalized": true,
394
+ "rstrip": false,
395
+ "single_word": false,
396
+ "special": false
397
+ },
398
+ "130099": {
399
+ "content": "<unused_token_17>",
400
+ "lstrip": false,
401
+ "normalized": true,
402
+ "rstrip": false,
403
+ "single_word": false,
404
+ "special": false
405
+ },
406
+ "130100": {
407
+ "content": "<unused_token_18>",
408
+ "lstrip": false,
409
+ "normalized": true,
410
+ "rstrip": false,
411
+ "single_word": false,
412
+ "special": false
413
+ },
414
+ "130101": {
415
+ "content": "<unused_token_19>",
416
+ "lstrip": false,
417
+ "normalized": true,
418
+ "rstrip": false,
419
+ "single_word": false,
420
+ "special": false
421
+ },
422
+ "130102": {
423
+ "content": "<unused_token_20>",
424
+ "lstrip": false,
425
+ "normalized": true,
426
+ "rstrip": false,
427
+ "single_word": false,
428
+ "special": false
429
+ },
430
+ "130103": {
431
+ "content": "<unused_token_21>",
432
+ "lstrip": false,
433
+ "normalized": true,
434
+ "rstrip": false,
435
+ "single_word": false,
436
+ "special": false
437
+ },
438
+ "130104": {
439
+ "content": "<unused_token_22>",
440
+ "lstrip": false,
441
+ "normalized": true,
442
+ "rstrip": false,
443
+ "single_word": false,
444
+ "special": false
445
+ },
446
+ "130105": {
447
+ "content": "<unused_token_23>",
448
+ "lstrip": false,
449
+ "normalized": true,
450
+ "rstrip": false,
451
+ "single_word": false,
452
+ "special": false
453
+ },
454
+ "130106": {
455
+ "content": "<unused_token_24>",
456
+ "lstrip": false,
457
+ "normalized": true,
458
+ "rstrip": false,
459
+ "single_word": false,
460
+ "special": false
461
+ },
462
+ "130107": {
463
+ "content": "<unused_token_25>",
464
+ "lstrip": false,
465
+ "normalized": true,
466
+ "rstrip": false,
467
+ "single_word": false,
468
+ "special": false
469
+ },
470
+ "130108": {
471
+ "content": "<unused_token_26>",
472
+ "lstrip": false,
473
+ "normalized": true,
474
+ "rstrip": false,
475
+ "single_word": false,
476
+ "special": false
477
+ },
478
+ "130109": {
479
+ "content": "<unused_token_27>",
480
+ "lstrip": false,
481
+ "normalized": true,
482
+ "rstrip": false,
483
+ "single_word": false,
484
+ "special": false
485
+ },
486
+ "130110": {
487
+ "content": "<unused_token_28>",
488
+ "lstrip": false,
489
+ "normalized": true,
490
+ "rstrip": false,
491
+ "single_word": false,
492
+ "special": false
493
+ },
494
+ "130111": {
495
+ "content": "<unused_token_29>",
496
+ "lstrip": false,
497
+ "normalized": true,
498
+ "rstrip": false,
499
+ "single_word": false,
500
+ "special": false
501
+ },
502
+ "130112": {
503
+ "content": "<unused_token_30>",
504
+ "lstrip": false,
505
+ "normalized": true,
506
+ "rstrip": false,
507
+ "single_word": false,
508
+ "special": false
509
+ },
510
+ "130113": {
511
+ "content": "<unused_token_31>",
512
+ "lstrip": false,
513
+ "normalized": true,
514
+ "rstrip": false,
515
+ "single_word": false,
516
+ "special": false
517
+ },
518
+ "130114": {
519
+ "content": "<unused_token_32>",
520
+ "lstrip": false,
521
+ "normalized": true,
522
+ "rstrip": false,
523
+ "single_word": false,
524
+ "special": false
525
+ },
526
+ "130115": {
527
+ "content": "<unused_token_33>",
528
+ "lstrip": false,
529
+ "normalized": true,
530
+ "rstrip": false,
531
+ "single_word": false,
532
+ "special": false
533
+ },
534
+ "130116": {
535
+ "content": "<unused_token_34>",
536
+ "lstrip": false,
537
+ "normalized": true,
538
+ "rstrip": false,
539
+ "single_word": false,
540
+ "special": false
541
+ },
542
+ "130117": {
543
+ "content": "<unused_token_35>",
544
+ "lstrip": false,
545
+ "normalized": true,
546
+ "rstrip": false,
547
+ "single_word": false,
548
+ "special": false
549
+ },
550
+ "130118": {
551
+ "content": "<unused_token_36>",
552
+ "lstrip": false,
553
+ "normalized": true,
554
+ "rstrip": false,
555
+ "single_word": false,
556
+ "special": false
557
+ },
558
+ "130119": {
559
+ "content": "<unused_token_37>",
560
+ "lstrip": false,
561
+ "normalized": true,
562
+ "rstrip": false,
563
+ "single_word": false,
564
+ "special": false
565
+ },
566
+ "130120": {
567
+ "content": "<unused_token_38>",
568
+ "lstrip": false,
569
+ "normalized": true,
570
+ "rstrip": false,
571
+ "single_word": false,
572
+ "special": false
573
+ },
574
+ "130121": {
575
+ "content": "<unused_token_39>",
576
+ "lstrip": false,
577
+ "normalized": true,
578
+ "rstrip": false,
579
+ "single_word": false,
580
+ "special": false
581
+ },
582
+ "130122": {
583
+ "content": "<unused_token_40>",
584
+ "lstrip": false,
585
+ "normalized": true,
586
+ "rstrip": false,
587
+ "single_word": false,
588
+ "special": false
589
+ },
590
+ "130123": {
591
+ "content": "<unused_token_41>",
592
+ "lstrip": false,
593
+ "normalized": true,
594
+ "rstrip": false,
595
+ "single_word": false,
596
+ "special": false
597
+ },
598
+ "130124": {
599
+ "content": "<unused_token_42>",
600
+ "lstrip": false,
601
+ "normalized": true,
602
+ "rstrip": false,
603
+ "single_word": false,
604
+ "special": false
605
+ },
606
+ "130125": {
607
+ "content": "<unused_token_43>",
608
+ "lstrip": false,
609
+ "normalized": true,
610
+ "rstrip": false,
611
+ "single_word": false,
612
+ "special": false
613
+ },
614
+ "130126": {
615
+ "content": "<unused_token_44>",
616
+ "lstrip": false,
617
+ "normalized": true,
618
+ "rstrip": false,
619
+ "single_word": false,
620
+ "special": false
621
+ },
622
+ "130127": {
623
+ "content": "<unused_token_45>",
624
+ "lstrip": false,
625
+ "normalized": true,
626
+ "rstrip": false,
627
+ "single_word": false,
628
+ "special": false
629
+ },
630
+ "130128": {
631
+ "content": "<unused_token_46>",
632
+ "lstrip": false,
633
+ "normalized": true,
634
+ "rstrip": false,
635
+ "single_word": false,
636
+ "special": false
637
+ },
638
+ "130129": {
639
+ "content": "<unused_token_47>",
640
+ "lstrip": false,
641
+ "normalized": true,
642
+ "rstrip": false,
643
+ "single_word": false,
644
+ "special": false
645
+ },
646
+ "130130": {
647
+ "content": "<unused_token_48>",
648
+ "lstrip": false,
649
+ "normalized": true,
650
+ "rstrip": false,
651
+ "single_word": false,
652
+ "special": false
653
+ },
654
+ "130131": {
655
+ "content": "<unused_token_49>",
656
+ "lstrip": false,
657
+ "normalized": true,
658
+ "rstrip": false,
659
+ "single_word": false,
660
+ "special": false
661
+ },
662
+ "130132": {
663
+ "content": "<unused_token_50>",
664
+ "lstrip": false,
665
+ "normalized": true,
666
+ "rstrip": false,
667
+ "single_word": false,
668
+ "special": false
669
+ },
670
+ "130133": {
671
+ "content": "<unused_token_51>",
672
+ "lstrip": false,
673
+ "normalized": true,
674
+ "rstrip": false,
675
+ "single_word": false,
676
+ "special": false
677
+ },
678
+ "130134": {
679
+ "content": "<unused_token_52>",
680
+ "lstrip": false,
681
+ "normalized": true,
682
+ "rstrip": false,
683
+ "single_word": false,
684
+ "special": false
685
+ },
686
+ "130135": {
687
+ "content": "<unused_token_53>",
688
+ "lstrip": false,
689
+ "normalized": true,
690
+ "rstrip": false,
691
+ "single_word": false,
692
+ "special": false
693
+ },
694
+ "130136": {
695
+ "content": "<unused_token_54>",
696
+ "lstrip": false,
697
+ "normalized": true,
698
+ "rstrip": false,
699
+ "single_word": false,
700
+ "special": false
701
+ },
702
+ "130137": {
703
+ "content": "<unused_token_55>",
704
+ "lstrip": false,
705
+ "normalized": true,
706
+ "rstrip": false,
707
+ "single_word": false,
708
+ "special": false
709
+ },
710
+ "130138": {
711
+ "content": "<unused_token_56>",
712
+ "lstrip": false,
713
+ "normalized": true,
714
+ "rstrip": false,
715
+ "single_word": false,
716
+ "special": false
717
+ },
718
+ "130139": {
719
+ "content": "<unused_token_57>",
720
+ "lstrip": false,
721
+ "normalized": true,
722
+ "rstrip": false,
723
+ "single_word": false,
724
+ "special": false
725
+ },
726
+ "130140": {
727
+ "content": "<unused_token_58>",
728
+ "lstrip": false,
729
+ "normalized": true,
730
+ "rstrip": false,
731
+ "single_word": false,
732
+ "special": false
733
+ },
734
+ "130141": {
735
+ "content": "<unused_token_59>",
736
+ "lstrip": false,
737
+ "normalized": true,
738
+ "rstrip": false,
739
+ "single_word": false,
740
+ "special": false
741
+ },
742
+ "130142": {
743
+ "content": "<unused_token_60>",
744
+ "lstrip": false,
745
+ "normalized": true,
746
+ "rstrip": false,
747
+ "single_word": false,
748
+ "special": false
749
+ },
750
+ "130143": {
751
+ "content": "<unused_token_61>",
752
+ "lstrip": false,
753
+ "normalized": true,
754
+ "rstrip": false,
755
+ "single_word": false,
756
+ "special": false
757
+ },
758
+ "130144": {
759
+ "content": "<unused_token_62>",
760
+ "lstrip": false,
761
+ "normalized": true,
762
+ "rstrip": false,
763
+ "single_word": false,
764
+ "special": false
765
+ },
766
+ "130145": {
767
+ "content": "<unused_token_63>",
768
+ "lstrip": false,
769
+ "normalized": true,
770
+ "rstrip": false,
771
+ "single_word": false,
772
+ "special": false
773
+ },
774
+ "130146": {
775
+ "content": "<unused_token_64>",
776
+ "lstrip": false,
777
+ "normalized": true,
778
+ "rstrip": false,
779
+ "single_word": false,
780
+ "special": false
781
+ },
782
+ "130147": {
783
+ "content": "<unused_token_65>",
784
+ "lstrip": false,
785
+ "normalized": true,
786
+ "rstrip": false,
787
+ "single_word": false,
788
+ "special": false
789
+ },
790
+ "130148": {
791
+ "content": "<unused_token_66>",
792
+ "lstrip": false,
793
+ "normalized": true,
794
+ "rstrip": false,
795
+ "single_word": false,
796
+ "special": false
797
+ },
798
+ "130149": {
799
+ "content": "<unused_token_67>",
800
+ "lstrip": false,
801
+ "normalized": true,
802
+ "rstrip": false,
803
+ "single_word": false,
804
+ "special": false
805
+ },
806
+ "130150": {
807
+ "content": "<unused_token_68>",
808
+ "lstrip": false,
809
+ "normalized": true,
810
+ "rstrip": false,
811
+ "single_word": false,
812
+ "special": false
813
+ },
814
+ "130151": {
815
+ "content": "<unused_token_69>",
816
+ "lstrip": false,
817
+ "normalized": true,
818
+ "rstrip": false,
819
+ "single_word": false,
820
+ "special": false
821
+ },
822
+ "130152": {
823
+ "content": "<unused_token_70>",
824
+ "lstrip": false,
825
+ "normalized": true,
826
+ "rstrip": false,
827
+ "single_word": false,
828
+ "special": false
829
+ },
830
+ "130153": {
831
+ "content": "<unused_token_71>",
832
+ "lstrip": false,
833
+ "normalized": true,
834
+ "rstrip": false,
835
+ "single_word": false,
836
+ "special": false
837
+ },
838
+ "130154": {
839
+ "content": "<unused_token_72>",
840
+ "lstrip": false,
841
+ "normalized": true,
842
+ "rstrip": false,
843
+ "single_word": false,
844
+ "special": false
845
+ },
846
+ "130155": {
847
+ "content": "<unused_token_73>",
848
+ "lstrip": false,
849
+ "normalized": true,
850
+ "rstrip": false,
851
+ "single_word": false,
852
+ "special": false
853
+ },
854
+ "130156": {
855
+ "content": "<unused_token_74>",
856
+ "lstrip": false,
857
+ "normalized": true,
858
+ "rstrip": false,
859
+ "single_word": false,
860
+ "special": false
861
+ },
862
+ "130157": {
863
+ "content": "<unused_token_75>",
864
+ "lstrip": false,
865
+ "normalized": true,
866
+ "rstrip": false,
867
+ "single_word": false,
868
+ "special": false
869
+ },
870
+ "130158": {
871
+ "content": "<unused_token_76>",
872
+ "lstrip": false,
873
+ "normalized": true,
874
+ "rstrip": false,
875
+ "single_word": false,
876
+ "special": false
877
+ },
878
+ "130159": {
879
+ "content": "<unused_token_77>",
880
+ "lstrip": false,
881
+ "normalized": true,
882
+ "rstrip": false,
883
+ "single_word": false,
884
+ "special": false
885
+ },
886
+ "130160": {
887
+ "content": "<unused_token_78>",
888
+ "lstrip": false,
889
+ "normalized": true,
890
+ "rstrip": false,
891
+ "single_word": false,
892
+ "special": false
893
+ },
894
+ "130161": {
895
+ "content": "<unused_token_79>",
896
+ "lstrip": false,
897
+ "normalized": true,
898
+ "rstrip": false,
899
+ "single_word": false,
900
+ "special": false
901
+ },
902
+ "130162": {
903
+ "content": "<unused_token_80>",
904
+ "lstrip": false,
905
+ "normalized": true,
906
+ "rstrip": false,
907
+ "single_word": false,
908
+ "special": false
909
+ },
910
+ "130163": {
911
+ "content": "<unused_token_81>",
912
+ "lstrip": false,
913
+ "normalized": true,
914
+ "rstrip": false,
915
+ "single_word": false,
916
+ "special": false
917
+ },
918
+ "130164": {
919
+ "content": "<unused_token_82>",
920
+ "lstrip": false,
921
+ "normalized": true,
922
+ "rstrip": false,
923
+ "single_word": false,
924
+ "special": false
925
+ },
926
+ "130165": {
927
+ "content": "<unused_token_83>",
928
+ "lstrip": false,
929
+ "normalized": true,
930
+ "rstrip": false,
931
+ "single_word": false,
932
+ "special": false
933
+ },
934
+ "130166": {
935
+ "content": "<unused_token_84>",
936
+ "lstrip": false,
937
+ "normalized": true,
938
+ "rstrip": false,
939
+ "single_word": false,
940
+ "special": false
941
+ },
942
+ "130167": {
943
+ "content": "<unused_token_85>",
944
+ "lstrip": false,
945
+ "normalized": true,
946
+ "rstrip": false,
947
+ "single_word": false,
948
+ "special": false
949
+ },
950
+ "130168": {
951
+ "content": "<unused_token_86>",
952
+ "lstrip": false,
953
+ "normalized": true,
954
+ "rstrip": false,
955
+ "single_word": false,
956
+ "special": false
957
+ },
958
+ "130169": {
959
+ "content": "<unused_token_87>",
960
+ "lstrip": false,
961
+ "normalized": true,
962
+ "rstrip": false,
963
+ "single_word": false,
964
+ "special": false
965
+ },
966
+ "130170": {
967
+ "content": "<unused_token_88>",
968
+ "lstrip": false,
969
+ "normalized": true,
970
+ "rstrip": false,
971
+ "single_word": false,
972
+ "special": false
973
+ },
974
+ "130171": {
975
+ "content": "<unused_token_89>",
976
+ "lstrip": false,
977
+ "normalized": true,
978
+ "rstrip": false,
979
+ "single_word": false,
980
+ "special": false
981
+ },
982
+ "130172": {
983
+ "content": "<unused_token_90>",
984
+ "lstrip": false,
985
+ "normalized": true,
986
+ "rstrip": false,
987
+ "single_word": false,
988
+ "special": false
989
+ },
990
+ "130173": {
991
+ "content": "<unused_token_91>",
992
+ "lstrip": false,
993
+ "normalized": true,
994
+ "rstrip": false,
995
+ "single_word": false,
996
+ "special": false
997
+ },
998
+ "130174": {
999
+ "content": "<unused_token_92>",
1000
+ "lstrip": false,
1001
+ "normalized": true,
1002
+ "rstrip": false,
1003
+ "single_word": false,
1004
+ "special": false
1005
+ },
1006
+ "130175": {
1007
+ "content": "<unused_token_93>",
1008
+ "lstrip": false,
1009
+ "normalized": true,
1010
+ "rstrip": false,
1011
+ "single_word": false,
1012
+ "special": false
1013
+ },
1014
+ "130176": {
1015
+ "content": "<unused_token_94>",
1016
+ "lstrip": false,
1017
+ "normalized": true,
1018
+ "rstrip": false,
1019
+ "single_word": false,
1020
+ "special": false
1021
+ },
1022
+ "130177": {
1023
+ "content": "<unused_token_95>",
1024
+ "lstrip": false,
1025
+ "normalized": true,
1026
+ "rstrip": false,
1027
+ "single_word": false,
1028
+ "special": false
1029
+ },
1030
+ "130178": {
1031
+ "content": "<unused_token_96>",
1032
+ "lstrip": false,
1033
+ "normalized": true,
1034
+ "rstrip": false,
1035
+ "single_word": false,
1036
+ "special": false
1037
+ },
1038
+ "130179": {
1039
+ "content": "<unused_token_97>",
1040
+ "lstrip": false,
1041
+ "normalized": true,
1042
+ "rstrip": false,
1043
+ "single_word": false,
1044
+ "special": false
1045
+ },
1046
+ "130180": {
1047
+ "content": "<unused_token_98>",
1048
+ "lstrip": false,
1049
+ "normalized": true,
1050
+ "rstrip": false,
1051
+ "single_word": false,
1052
+ "special": false
1053
+ },
1054
+ "130181": {
1055
+ "content": "<unused_token_99>",
1056
+ "lstrip": false,
1057
+ "normalized": true,
1058
+ "rstrip": false,
1059
+ "single_word": false,
1060
+ "special": false
1061
+ },
1062
+ "130182": {
1063
+ "content": "<unused_token_100>",
1064
+ "lstrip": false,
1065
+ "normalized": true,
1066
+ "rstrip": false,
1067
+ "single_word": false,
1068
+ "special": false
1069
+ },
1070
+ "130183": {
1071
+ "content": "<unused_token_101>",
1072
+ "lstrip": false,
1073
+ "normalized": true,
1074
+ "rstrip": false,
1075
+ "single_word": false,
1076
+ "special": false
1077
+ },
1078
+ "130184": {
1079
+ "content": "<unused_token_102>",
1080
+ "lstrip": false,
1081
+ "normalized": true,
1082
+ "rstrip": false,
1083
+ "single_word": false,
1084
+ "special": false
1085
+ },
1086
+ "130185": {
1087
+ "content": "<unused_token_103>",
1088
+ "lstrip": false,
1089
+ "normalized": true,
1090
+ "rstrip": false,
1091
+ "single_word": false,
1092
+ "special": false
1093
+ },
1094
+ "130186": {
1095
+ "content": "<unused_token_104>",
1096
+ "lstrip": false,
1097
+ "normalized": true,
1098
+ "rstrip": false,
1099
+ "single_word": false,
1100
+ "special": false
1101
+ },
1102
+ "130187": {
1103
+ "content": "<unused_token_105>",
1104
+ "lstrip": false,
1105
+ "normalized": true,
1106
+ "rstrip": false,
1107
+ "single_word": false,
1108
+ "special": false
1109
+ },
1110
+ "130188": {
1111
+ "content": "<unused_token_106>",
1112
+ "lstrip": false,
1113
+ "normalized": true,
1114
+ "rstrip": false,
1115
+ "single_word": false,
1116
+ "special": false
1117
+ },
1118
+ "130189": {
1119
+ "content": "<unused_token_107>",
1120
+ "lstrip": false,
1121
+ "normalized": true,
1122
+ "rstrip": false,
1123
+ "single_word": false,
1124
+ "special": false
1125
+ },
1126
+ "130190": {
1127
+ "content": "<unused_token_108>",
1128
+ "lstrip": false,
1129
+ "normalized": true,
1130
+ "rstrip": false,
1131
+ "single_word": false,
1132
+ "special": false
1133
+ },
1134
+ "130191": {
1135
+ "content": "<unused_token_109>",
1136
+ "lstrip": false,
1137
+ "normalized": true,
1138
+ "rstrip": false,
1139
+ "single_word": false,
1140
+ "special": false
1141
+ },
1142
+ "130192": {
1143
+ "content": "<unused_token_110>",
1144
+ "lstrip": false,
1145
+ "normalized": true,
1146
+ "rstrip": false,
1147
+ "single_word": false,
1148
+ "special": false
1149
+ },
1150
+ "130193": {
1151
+ "content": "<unused_token_111>",
1152
+ "lstrip": false,
1153
+ "normalized": true,
1154
+ "rstrip": false,
1155
+ "single_word": false,
1156
+ "special": false
1157
+ },
1158
+ "130194": {
1159
+ "content": "<unused_token_112>",
1160
+ "lstrip": false,
1161
+ "normalized": true,
1162
+ "rstrip": false,
1163
+ "single_word": false,
1164
+ "special": false
1165
+ },
1166
+ "130195": {
1167
+ "content": "<unused_token_113>",
1168
+ "lstrip": false,
1169
+ "normalized": true,
1170
+ "rstrip": false,
1171
+ "single_word": false,
1172
+ "special": false
1173
+ },
1174
+ "130196": {
1175
+ "content": "<unused_token_114>",
1176
+ "lstrip": false,
1177
+ "normalized": true,
1178
+ "rstrip": false,
1179
+ "single_word": false,
1180
+ "special": false
1181
+ },
1182
+ "130197": {
1183
+ "content": "<unused_token_115>",
1184
+ "lstrip": false,
1185
+ "normalized": true,
1186
+ "rstrip": false,
1187
+ "single_word": false,
1188
+ "special": false
1189
+ },
1190
+ "130198": {
1191
+ "content": "<unused_token_116>",
1192
+ "lstrip": false,
1193
+ "normalized": true,
1194
+ "rstrip": false,
1195
+ "single_word": false,
1196
+ "special": false
1197
+ },
1198
+ "130199": {
1199
+ "content": "<unused_token_117>",
1200
+ "lstrip": false,
1201
+ "normalized": true,
1202
+ "rstrip": false,
1203
+ "single_word": false,
1204
+ "special": false
1205
+ },
1206
+ "130200": {
1207
+ "content": "<unused_token_118>",
1208
+ "lstrip": false,
1209
+ "normalized": true,
1210
+ "rstrip": false,
1211
+ "single_word": false,
1212
+ "special": false
1213
+ },
1214
+ "130201": {
1215
+ "content": "<unused_token_119>",
1216
+ "lstrip": false,
1217
+ "normalized": true,
1218
+ "rstrip": false,
1219
+ "single_word": false,
1220
+ "special": false
1221
+ },
1222
+ "130202": {
1223
+ "content": "<unused_token_120>",
1224
+ "lstrip": false,
1225
+ "normalized": true,
1226
+ "rstrip": false,
1227
+ "single_word": false,
1228
+ "special": false
1229
+ },
1230
+ "130203": {
1231
+ "content": "<unused_token_121>",
1232
+ "lstrip": false,
1233
+ "normalized": true,
1234
+ "rstrip": false,
1235
+ "single_word": false,
1236
+ "special": false
1237
+ },
1238
+ "130204": {
1239
+ "content": "<unused_token_122>",
1240
+ "lstrip": false,
1241
+ "normalized": true,
1242
+ "rstrip": false,
1243
+ "single_word": false,
1244
+ "special": false
1245
+ },
1246
+ "130205": {
1247
+ "content": "<unused_token_123>",
1248
+ "lstrip": false,
1249
+ "normalized": true,
1250
+ "rstrip": false,
1251
+ "single_word": false,
1252
+ "special": false
1253
+ },
1254
+ "130206": {
1255
+ "content": "<unused_token_124>",
1256
+ "lstrip": false,
1257
+ "normalized": true,
1258
+ "rstrip": false,
1259
+ "single_word": false,
1260
+ "special": false
1261
+ },
1262
+ "130207": {
1263
+ "content": "<unused_token_125>",
1264
+ "lstrip": false,
1265
+ "normalized": true,
1266
+ "rstrip": false,
1267
+ "single_word": false,
1268
+ "special": false
1269
+ },
1270
+ "130208": {
1271
+ "content": "<unused_token_126>",
1272
+ "lstrip": false,
1273
+ "normalized": true,
1274
+ "rstrip": false,
1275
+ "single_word": false,
1276
+ "special": false
1277
+ },
1278
+ "130209": {
1279
+ "content": "<unused_token_127>",
1280
+ "lstrip": false,
1281
+ "normalized": true,
1282
+ "rstrip": false,
1283
+ "single_word": false,
1284
+ "special": false
1285
+ },
1286
+ "130210": {
1287
+ "content": "<unused_token_128>",
1288
+ "lstrip": false,
1289
+ "normalized": true,
1290
+ "rstrip": false,
1291
+ "single_word": false,
1292
+ "special": false
1293
+ },
1294
+ "130211": {
1295
+ "content": "<unused_token_129>",
1296
+ "lstrip": false,
1297
+ "normalized": true,
1298
+ "rstrip": false,
1299
+ "single_word": false,
1300
+ "special": false
1301
+ },
1302
+ "130212": {
1303
+ "content": "<unused_token_130>",
1304
+ "lstrip": false,
1305
+ "normalized": true,
1306
+ "rstrip": false,
1307
+ "single_word": false,
1308
+ "special": false
1309
+ },
1310
+ "130213": {
1311
+ "content": "<unused_token_131>",
1312
+ "lstrip": false,
1313
+ "normalized": true,
1314
+ "rstrip": false,
1315
+ "single_word": false,
1316
+ "special": false
1317
+ },
1318
+ "130214": {
1319
+ "content": "<unused_token_132>",
1320
+ "lstrip": false,
1321
+ "normalized": true,
1322
+ "rstrip": false,
1323
+ "single_word": false,
1324
+ "special": false
1325
+ },
1326
+ "130215": {
1327
+ "content": "<unused_token_133>",
1328
+ "lstrip": false,
1329
+ "normalized": true,
1330
+ "rstrip": false,
1331
+ "single_word": false,
1332
+ "special": false
1333
+ },
1334
+ "130216": {
1335
+ "content": "<unused_token_134>",
1336
+ "lstrip": false,
1337
+ "normalized": true,
1338
+ "rstrip": false,
1339
+ "single_word": false,
1340
+ "special": false
1341
+ },
1342
+ "130217": {
1343
+ "content": "<unused_token_135>",
1344
+ "lstrip": false,
1345
+ "normalized": true,
1346
+ "rstrip": false,
1347
+ "single_word": false,
1348
+ "special": false
1349
+ },
1350
+ "130218": {
1351
+ "content": "<unused_token_136>",
1352
+ "lstrip": false,
1353
+ "normalized": true,
1354
+ "rstrip": false,
1355
+ "single_word": false,
1356
+ "special": false
1357
+ },
1358
+ "130219": {
1359
+ "content": "<unused_token_137>",
1360
+ "lstrip": false,
1361
+ "normalized": true,
1362
+ "rstrip": false,
1363
+ "single_word": false,
1364
+ "special": false
1365
+ },
1366
+ "130220": {
1367
+ "content": "<unused_token_138>",
1368
+ "lstrip": false,
1369
+ "normalized": true,
1370
+ "rstrip": false,
1371
+ "single_word": false,
1372
+ "special": false
1373
+ },
1374
+ "130221": {
1375
+ "content": "<unused_token_139>",
1376
+ "lstrip": false,
1377
+ "normalized": true,
1378
+ "rstrip": false,
1379
+ "single_word": false,
1380
+ "special": false
1381
+ },
1382
+ "130222": {
1383
+ "content": "<unused_token_140>",
1384
+ "lstrip": false,
1385
+ "normalized": true,
1386
+ "rstrip": false,
1387
+ "single_word": false,
1388
+ "special": false
1389
+ },
1390
+ "130223": {
1391
+ "content": "<unused_token_141>",
1392
+ "lstrip": false,
1393
+ "normalized": true,
1394
+ "rstrip": false,
1395
+ "single_word": false,
1396
+ "special": false
1397
+ },
1398
+ "130224": {
1399
+ "content": "<unused_token_142>",
1400
+ "lstrip": false,
1401
+ "normalized": true,
1402
+ "rstrip": false,
1403
+ "single_word": false,
1404
+ "special": false
1405
+ },
1406
+ "130225": {
1407
+ "content": "<unused_token_143>",
1408
+ "lstrip": false,
1409
+ "normalized": true,
1410
+ "rstrip": false,
1411
+ "single_word": false,
1412
+ "special": false
1413
+ },
1414
+ "130226": {
1415
+ "content": "<unused_token_144>",
1416
+ "lstrip": false,
1417
+ "normalized": true,
1418
+ "rstrip": false,
1419
+ "single_word": false,
1420
+ "special": false
1421
+ },
1422
+ "130227": {
1423
+ "content": "<unused_token_145>",
1424
+ "lstrip": false,
1425
+ "normalized": true,
1426
+ "rstrip": false,
1427
+ "single_word": false,
1428
+ "special": false
1429
+ },
1430
+ "130228": {
1431
+ "content": "<unused_token_146>",
1432
+ "lstrip": false,
1433
+ "normalized": true,
1434
+ "rstrip": false,
1435
+ "single_word": false,
1436
+ "special": false
1437
+ },
1438
+ "130229": {
1439
+ "content": "<unused_token_147>",
1440
+ "lstrip": false,
1441
+ "normalized": true,
1442
+ "rstrip": false,
1443
+ "single_word": false,
1444
+ "special": false
1445
+ },
1446
+ "130230": {
1447
+ "content": "<unused_token_148>",
1448
+ "lstrip": false,
1449
+ "normalized": true,
1450
+ "rstrip": false,
1451
+ "single_word": false,
1452
+ "special": false
1453
+ },
1454
+ "130231": {
1455
+ "content": "<unused_token_149>",
1456
+ "lstrip": false,
1457
+ "normalized": true,
1458
+ "rstrip": false,
1459
+ "single_word": false,
1460
+ "special": false
1461
+ },
1462
+ "130232": {
1463
+ "content": "<unused_token_150>",
1464
+ "lstrip": false,
1465
+ "normalized": true,
1466
+ "rstrip": false,
1467
+ "single_word": false,
1468
+ "special": false
1469
+ },
1470
+ "130233": {
1471
+ "content": "<unused_token_151>",
1472
+ "lstrip": false,
1473
+ "normalized": true,
1474
+ "rstrip": false,
1475
+ "single_word": false,
1476
+ "special": false
1477
+ },
1478
+ "130234": {
1479
+ "content": "<unused_token_152>",
1480
+ "lstrip": false,
1481
+ "normalized": true,
1482
+ "rstrip": false,
1483
+ "single_word": false,
1484
+ "special": false
1485
+ },
1486
+ "130235": {
1487
+ "content": "<unused_token_153>",
1488
+ "lstrip": false,
1489
+ "normalized": true,
1490
+ "rstrip": false,
1491
+ "single_word": false,
1492
+ "special": false
1493
+ },
1494
+ "130236": {
1495
+ "content": "<unused_token_154>",
1496
+ "lstrip": false,
1497
+ "normalized": true,
1498
+ "rstrip": false,
1499
+ "single_word": false,
1500
+ "special": false
1501
+ },
1502
+ "130237": {
1503
+ "content": "<unused_token_155>",
1504
+ "lstrip": false,
1505
+ "normalized": true,
1506
+ "rstrip": false,
1507
+ "single_word": false,
1508
+ "special": false
1509
+ },
1510
+ "130238": {
1511
+ "content": "<unused_token_156>",
1512
+ "lstrip": false,
1513
+ "normalized": true,
1514
+ "rstrip": false,
1515
+ "single_word": false,
1516
+ "special": false
1517
+ },
1518
+ "130239": {
1519
+ "content": "<unused_token_157>",
1520
+ "lstrip": false,
1521
+ "normalized": true,
1522
+ "rstrip": false,
1523
+ "single_word": false,
1524
+ "special": false
1525
+ },
1526
+ "130240": {
1527
+ "content": "<unused_token_158>",
1528
+ "lstrip": false,
1529
+ "normalized": true,
1530
+ "rstrip": false,
1531
+ "single_word": false,
1532
+ "special": false
1533
+ },
1534
+ "130241": {
1535
+ "content": "<unused_token_159>",
1536
+ "lstrip": false,
1537
+ "normalized": true,
1538
+ "rstrip": false,
1539
+ "single_word": false,
1540
+ "special": false
1541
+ },
1542
+ "130242": {
1543
+ "content": "<unused_token_160>",
1544
+ "lstrip": false,
1545
+ "normalized": true,
1546
+ "rstrip": false,
1547
+ "single_word": false,
1548
+ "special": false
1549
+ },
1550
+ "130243": {
1551
+ "content": "<unused_token_161>",
1552
+ "lstrip": false,
1553
+ "normalized": true,
1554
+ "rstrip": false,
1555
+ "single_word": false,
1556
+ "special": false
1557
+ },
1558
+ "130244": {
1559
+ "content": "<unused_token_162>",
1560
+ "lstrip": false,
1561
+ "normalized": true,
1562
+ "rstrip": false,
1563
+ "single_word": false,
1564
+ "special": false
1565
+ },
1566
+ "130245": {
1567
+ "content": "<unused_token_163>",
1568
+ "lstrip": false,
1569
+ "normalized": true,
1570
+ "rstrip": false,
1571
+ "single_word": false,
1572
+ "special": false
1573
+ },
1574
+ "130246": {
1575
+ "content": "<unused_token_164>",
1576
+ "lstrip": false,
1577
+ "normalized": true,
1578
+ "rstrip": false,
1579
+ "single_word": false,
1580
+ "special": false
1581
+ },
1582
+ "130247": {
1583
+ "content": "<unused_token_165>",
1584
+ "lstrip": false,
1585
+ "normalized": true,
1586
+ "rstrip": false,
1587
+ "single_word": false,
1588
+ "special": false
1589
+ },
1590
+ "130248": {
1591
+ "content": "<unused_token_166>",
1592
+ "lstrip": false,
1593
+ "normalized": true,
1594
+ "rstrip": false,
1595
+ "single_word": false,
1596
+ "special": false
1597
+ },
1598
+ "130249": {
1599
+ "content": "<unused_token_167>",
1600
+ "lstrip": false,
1601
+ "normalized": true,
1602
+ "rstrip": false,
1603
+ "single_word": false,
1604
+ "special": false
1605
+ },
1606
+ "130250": {
1607
+ "content": "<unused_token_168>",
1608
+ "lstrip": false,
1609
+ "normalized": true,
1610
+ "rstrip": false,
1611
+ "single_word": false,
1612
+ "special": false
1613
+ },
1614
+ "130251": {
1615
+ "content": "<unused_token_169>",
1616
+ "lstrip": false,
1617
+ "normalized": true,
1618
+ "rstrip": false,
1619
+ "single_word": false,
1620
+ "special": false
1621
+ },
1622
+ "130252": {
1623
+ "content": "<unused_token_170>",
1624
+ "lstrip": false,
1625
+ "normalized": true,
1626
+ "rstrip": false,
1627
+ "single_word": false,
1628
+ "special": false
1629
+ },
1630
+ "130253": {
1631
+ "content": "<unused_token_171>",
1632
+ "lstrip": false,
1633
+ "normalized": true,
1634
+ "rstrip": false,
1635
+ "single_word": false,
1636
+ "special": false
1637
+ },
1638
+ "130254": {
1639
+ "content": "<unused_token_172>",
1640
+ "lstrip": false,
1641
+ "normalized": true,
1642
+ "rstrip": false,
1643
+ "single_word": false,
1644
+ "special": false
1645
+ },
1646
+ "130255": {
1647
+ "content": "<unused_token_173>",
1648
+ "lstrip": false,
1649
+ "normalized": true,
1650
+ "rstrip": false,
1651
+ "single_word": false,
1652
+ "special": false
1653
+ },
1654
+ "130256": {
1655
+ "content": "<unused_token_174>",
1656
+ "lstrip": false,
1657
+ "normalized": true,
1658
+ "rstrip": false,
1659
+ "single_word": false,
1660
+ "special": false
1661
+ },
1662
+ "130257": {
1663
+ "content": "<unused_token_175>",
1664
+ "lstrip": false,
1665
+ "normalized": true,
1666
+ "rstrip": false,
1667
+ "single_word": false,
1668
+ "special": false
1669
+ },
1670
+ "130258": {
1671
+ "content": "<unused_token_176>",
1672
+ "lstrip": false,
1673
+ "normalized": true,
1674
+ "rstrip": false,
1675
+ "single_word": false,
1676
+ "special": false
1677
+ },
1678
+ "130259": {
1679
+ "content": "<unused_token_177>",
1680
+ "lstrip": false,
1681
+ "normalized": true,
1682
+ "rstrip": false,
1683
+ "single_word": false,
1684
+ "special": false
1685
+ },
1686
+ "130260": {
1687
+ "content": "<unused_token_178>",
1688
+ "lstrip": false,
1689
+ "normalized": true,
1690
+ "rstrip": false,
1691
+ "single_word": false,
1692
+ "special": false
1693
+ },
1694
+ "130261": {
1695
+ "content": "<unused_token_179>",
1696
+ "lstrip": false,
1697
+ "normalized": true,
1698
+ "rstrip": false,
1699
+ "single_word": false,
1700
+ "special": false
1701
+ },
1702
+ "130262": {
1703
+ "content": "<unused_token_180>",
1704
+ "lstrip": false,
1705
+ "normalized": true,
1706
+ "rstrip": false,
1707
+ "single_word": false,
1708
+ "special": false
1709
+ },
1710
+ "130263": {
1711
+ "content": "<unused_token_181>",
1712
+ "lstrip": false,
1713
+ "normalized": true,
1714
+ "rstrip": false,
1715
+ "single_word": false,
1716
+ "special": false
1717
+ },
1718
+ "130264": {
1719
+ "content": "<unused_token_182>",
1720
+ "lstrip": false,
1721
+ "normalized": true,
1722
+ "rstrip": false,
1723
+ "single_word": false,
1724
+ "special": false
1725
+ },
1726
+ "130265": {
1727
+ "content": "<unused_token_183>",
1728
+ "lstrip": false,
1729
+ "normalized": true,
1730
+ "rstrip": false,
1731
+ "single_word": false,
1732
+ "special": false
1733
+ },
1734
+ "130266": {
1735
+ "content": "<unused_token_184>",
1736
+ "lstrip": false,
1737
+ "normalized": true,
1738
+ "rstrip": false,
1739
+ "single_word": false,
1740
+ "special": false
1741
+ },
1742
+ "130267": {
1743
+ "content": "<unused_token_185>",
1744
+ "lstrip": false,
1745
+ "normalized": true,
1746
+ "rstrip": false,
1747
+ "single_word": false,
1748
+ "special": false
1749
+ },
1750
+ "130268": {
1751
+ "content": "<unused_token_186>",
1752
+ "lstrip": false,
1753
+ "normalized": true,
1754
+ "rstrip": false,
1755
+ "single_word": false,
1756
+ "special": false
1757
+ },
1758
+ "130269": {
1759
+ "content": "<unused_token_187>",
1760
+ "lstrip": false,
1761
+ "normalized": true,
1762
+ "rstrip": false,
1763
+ "single_word": false,
1764
+ "special": false
1765
+ },
1766
+ "130270": {
1767
+ "content": "<unused_token_188>",
1768
+ "lstrip": false,
1769
+ "normalized": true,
1770
+ "rstrip": false,
1771
+ "single_word": false,
1772
+ "special": false
1773
+ },
1774
+ "130271": {
1775
+ "content": "<unused_token_189>",
1776
+ "lstrip": false,
1777
+ "normalized": true,
1778
+ "rstrip": false,
1779
+ "single_word": false,
1780
+ "special": false
1781
+ },
1782
+ "130272": {
1783
+ "content": "<unused_token_190>",
1784
+ "lstrip": false,
1785
+ "normalized": true,
1786
+ "rstrip": false,
1787
+ "single_word": false,
1788
+ "special": false
1789
+ },
1790
+ "130273": {
1791
+ "content": "<unused_token_191>",
1792
+ "lstrip": false,
1793
+ "normalized": true,
1794
+ "rstrip": false,
1795
+ "single_word": false,
1796
+ "special": false
1797
+ },
1798
+ "130274": {
1799
+ "content": "<unused_token_192>",
1800
+ "lstrip": false,
1801
+ "normalized": true,
1802
+ "rstrip": false,
1803
+ "single_word": false,
1804
+ "special": false
1805
+ },
1806
+ "130275": {
1807
+ "content": "<unused_token_193>",
1808
+ "lstrip": false,
1809
+ "normalized": true,
1810
+ "rstrip": false,
1811
+ "single_word": false,
1812
+ "special": false
1813
+ },
1814
+ "130276": {
1815
+ "content": "<unused_token_194>",
1816
+ "lstrip": false,
1817
+ "normalized": true,
1818
+ "rstrip": false,
1819
+ "single_word": false,
1820
+ "special": false
1821
+ },
1822
+ "130277": {
1823
+ "content": "<unused_token_195>",
1824
+ "lstrip": false,
1825
+ "normalized": true,
1826
+ "rstrip": false,
1827
+ "single_word": false,
1828
+ "special": false
1829
+ },
1830
+ "130278": {
1831
+ "content": "<unused_token_196>",
1832
+ "lstrip": false,
1833
+ "normalized": true,
1834
+ "rstrip": false,
1835
+ "single_word": false,
1836
+ "special": false
1837
+ },
1838
+ "130279": {
1839
+ "content": "<unused_token_197>",
1840
+ "lstrip": false,
1841
+ "normalized": true,
1842
+ "rstrip": false,
1843
+ "single_word": false,
1844
+ "special": false
1845
+ },
1846
+ "130280": {
1847
+ "content": "<unused_token_198>",
1848
+ "lstrip": false,
1849
+ "normalized": true,
1850
+ "rstrip": false,
1851
+ "single_word": false,
1852
+ "special": false
1853
+ },
1854
+ "130281": {
1855
+ "content": "<unused_token_199>",
1856
+ "lstrip": false,
1857
+ "normalized": true,
1858
+ "rstrip": false,
1859
+ "single_word": false,
1860
+ "special": false
1861
+ },
1862
+ "130282": {
1863
+ "content": "<unused_token_200>",
1864
+ "lstrip": false,
1865
+ "normalized": true,
1866
+ "rstrip": false,
1867
+ "single_word": false,
1868
+ "special": false
1869
+ },
1870
+ "130283": {
1871
+ "content": "<unused_token_201>",
1872
+ "lstrip": false,
1873
+ "normalized": true,
1874
+ "rstrip": false,
1875
+ "single_word": false,
1876
+ "special": false
1877
+ },
1878
+ "130284": {
1879
+ "content": "<unused_token_202>",
1880
+ "lstrip": false,
1881
+ "normalized": true,
1882
+ "rstrip": false,
1883
+ "single_word": false,
1884
+ "special": false
1885
+ },
1886
+ "130285": {
1887
+ "content": "<unused_token_203>",
1888
+ "lstrip": false,
1889
+ "normalized": true,
1890
+ "rstrip": false,
1891
+ "single_word": false,
1892
+ "special": false
1893
+ },
1894
+ "130286": {
1895
+ "content": "<unused_token_204>",
1896
+ "lstrip": false,
1897
+ "normalized": true,
1898
+ "rstrip": false,
1899
+ "single_word": false,
1900
+ "special": false
1901
+ },
1902
+ "130287": {
1903
+ "content": "<unused_token_205>",
1904
+ "lstrip": false,
1905
+ "normalized": true,
1906
+ "rstrip": false,
1907
+ "single_word": false,
1908
+ "special": false
1909
+ },
1910
+ "130288": {
1911
+ "content": "<unused_token_206>",
1912
+ "lstrip": false,
1913
+ "normalized": true,
1914
+ "rstrip": false,
1915
+ "single_word": false,
1916
+ "special": false
1917
+ },
1918
+ "130289": {
1919
+ "content": "<unused_token_207>",
1920
+ "lstrip": false,
1921
+ "normalized": true,
1922
+ "rstrip": false,
1923
+ "single_word": false,
1924
+ "special": false
1925
+ },
1926
+ "130290": {
1927
+ "content": "<unused_token_208>",
1928
+ "lstrip": false,
1929
+ "normalized": true,
1930
+ "rstrip": false,
1931
+ "single_word": false,
1932
+ "special": false
1933
+ },
1934
+ "130291": {
1935
+ "content": "<unused_token_209>",
1936
+ "lstrip": false,
1937
+ "normalized": true,
1938
+ "rstrip": false,
1939
+ "single_word": false,
1940
+ "special": false
1941
+ },
1942
+ "130292": {
1943
+ "content": "<unused_token_210>",
1944
+ "lstrip": false,
1945
+ "normalized": true,
1946
+ "rstrip": false,
1947
+ "single_word": false,
1948
+ "special": false
1949
+ },
1950
+ "130293": {
1951
+ "content": "<unused_token_211>",
1952
+ "lstrip": false,
1953
+ "normalized": true,
1954
+ "rstrip": false,
1955
+ "single_word": false,
1956
+ "special": false
1957
+ },
1958
+ "130294": {
1959
+ "content": "<unused_token_212>",
1960
+ "lstrip": false,
1961
+ "normalized": true,
1962
+ "rstrip": false,
1963
+ "single_word": false,
1964
+ "special": false
1965
+ },
1966
+ "130295": {
1967
+ "content": "<unused_token_213>",
1968
+ "lstrip": false,
1969
+ "normalized": true,
1970
+ "rstrip": false,
1971
+ "single_word": false,
1972
+ "special": false
1973
+ },
1974
+ "130296": {
1975
+ "content": "<unused_token_214>",
1976
+ "lstrip": false,
1977
+ "normalized": true,
1978
+ "rstrip": false,
1979
+ "single_word": false,
1980
+ "special": false
1981
+ },
1982
+ "130297": {
1983
+ "content": "<unused_token_215>",
1984
+ "lstrip": false,
1985
+ "normalized": true,
1986
+ "rstrip": false,
1987
+ "single_word": false,
1988
+ "special": false
1989
+ },
1990
+ "130298": {
1991
+ "content": "<unused_token_216>",
1992
+ "lstrip": false,
1993
+ "normalized": true,
1994
+ "rstrip": false,
1995
+ "single_word": false,
1996
+ "special": false
1997
+ },
1998
+ "130299": {
1999
+ "content": "<unused_token_217>",
2000
+ "lstrip": false,
2001
+ "normalized": true,
2002
+ "rstrip": false,
2003
+ "single_word": false,
2004
+ "special": false
2005
+ },
2006
+ "130300": {
2007
+ "content": "<unused_token_218>",
2008
+ "lstrip": false,
2009
+ "normalized": true,
2010
+ "rstrip": false,
2011
+ "single_word": false,
2012
+ "special": false
2013
+ },
2014
+ "130301": {
2015
+ "content": "<unused_token_219>",
2016
+ "lstrip": false,
2017
+ "normalized": true,
2018
+ "rstrip": false,
2019
+ "single_word": false,
2020
+ "special": false
2021
+ },
2022
+ "130302": {
2023
+ "content": "<unused_token_220>",
2024
+ "lstrip": false,
2025
+ "normalized": true,
2026
+ "rstrip": false,
2027
+ "single_word": false,
2028
+ "special": false
2029
+ },
2030
+ "130303": {
2031
+ "content": "<unused_token_221>",
2032
+ "lstrip": false,
2033
+ "normalized": true,
2034
+ "rstrip": false,
2035
+ "single_word": false,
2036
+ "special": false
2037
+ },
2038
+ "130304": {
2039
+ "content": "<unused_token_222>",
2040
+ "lstrip": false,
2041
+ "normalized": true,
2042
+ "rstrip": false,
2043
+ "single_word": false,
2044
+ "special": false
2045
+ },
2046
+ "130305": {
2047
+ "content": "<unused_token_223>",
2048
+ "lstrip": false,
2049
+ "normalized": true,
2050
+ "rstrip": false,
2051
+ "single_word": false,
2052
+ "special": false
2053
+ },
2054
+ "130306": {
2055
+ "content": "<unused_token_224>",
2056
+ "lstrip": false,
2057
+ "normalized": true,
2058
+ "rstrip": false,
2059
+ "single_word": false,
2060
+ "special": false
2061
+ },
2062
+ "130307": {
2063
+ "content": "<unused_token_225>",
2064
+ "lstrip": false,
2065
+ "normalized": true,
2066
+ "rstrip": false,
2067
+ "single_word": false,
2068
+ "special": false
2069
+ },
2070
+ "130308": {
2071
+ "content": "<unused_token_226>",
2072
+ "lstrip": false,
2073
+ "normalized": true,
2074
+ "rstrip": false,
2075
+ "single_word": false,
2076
+ "special": false
2077
+ },
2078
+ "130309": {
2079
+ "content": "<unused_token_227>",
2080
+ "lstrip": false,
2081
+ "normalized": true,
2082
+ "rstrip": false,
2083
+ "single_word": false,
2084
+ "special": false
2085
+ },
2086
+ "130310": {
2087
+ "content": "<unused_token_228>",
2088
+ "lstrip": false,
2089
+ "normalized": true,
2090
+ "rstrip": false,
2091
+ "single_word": false,
2092
+ "special": false
2093
+ },
2094
+ "130311": {
2095
+ "content": "<unused_token_229>",
2096
+ "lstrip": false,
2097
+ "normalized": true,
2098
+ "rstrip": false,
2099
+ "single_word": false,
2100
+ "special": false
2101
+ },
2102
+ "130312": {
2103
+ "content": "<unused_token_230>",
2104
+ "lstrip": false,
2105
+ "normalized": true,
2106
+ "rstrip": false,
2107
+ "single_word": false,
2108
+ "special": false
2109
+ },
2110
+ "130313": {
2111
+ "content": "<unused_token_231>",
2112
+ "lstrip": false,
2113
+ "normalized": true,
2114
+ "rstrip": false,
2115
+ "single_word": false,
2116
+ "special": false
2117
+ },
2118
+ "130314": {
2119
+ "content": "<unused_token_232>",
2120
+ "lstrip": false,
2121
+ "normalized": true,
2122
+ "rstrip": false,
2123
+ "single_word": false,
2124
+ "special": false
2125
+ },
2126
+ "130315": {
2127
+ "content": "<unused_token_233>",
2128
+ "lstrip": false,
2129
+ "normalized": true,
2130
+ "rstrip": false,
2131
+ "single_word": false,
2132
+ "special": false
2133
+ },
2134
+ "130316": {
2135
+ "content": "<unused_token_234>",
2136
+ "lstrip": false,
2137
+ "normalized": true,
2138
+ "rstrip": false,
2139
+ "single_word": false,
2140
+ "special": false
2141
+ },
2142
+ "130317": {
2143
+ "content": "<unused_token_235>",
2144
+ "lstrip": false,
2145
+ "normalized": true,
2146
+ "rstrip": false,
2147
+ "single_word": false,
2148
+ "special": false
2149
+ },
2150
+ "130318": {
2151
+ "content": "<unused_token_236>",
2152
+ "lstrip": false,
2153
+ "normalized": true,
2154
+ "rstrip": false,
2155
+ "single_word": false,
2156
+ "special": false
2157
+ },
2158
+ "130319": {
2159
+ "content": "<unused_token_237>",
2160
+ "lstrip": false,
2161
+ "normalized": true,
2162
+ "rstrip": false,
2163
+ "single_word": false,
2164
+ "special": false
2165
+ },
2166
+ "130320": {
2167
+ "content": "<unused_token_238>",
2168
+ "lstrip": false,
2169
+ "normalized": true,
2170
+ "rstrip": false,
2171
+ "single_word": false,
2172
+ "special": false
2173
+ },
2174
+ "130321": {
2175
+ "content": "<unused_token_239>",
2176
+ "lstrip": false,
2177
+ "normalized": true,
2178
+ "rstrip": false,
2179
+ "single_word": false,
2180
+ "special": false
2181
+ },
2182
+ "130322": {
2183
+ "content": "<unused_token_240>",
2184
+ "lstrip": false,
2185
+ "normalized": true,
2186
+ "rstrip": false,
2187
+ "single_word": false,
2188
+ "special": false
2189
+ },
2190
+ "130323": {
2191
+ "content": "<unused_token_241>",
2192
+ "lstrip": false,
2193
+ "normalized": true,
2194
+ "rstrip": false,
2195
+ "single_word": false,
2196
+ "special": false
2197
+ },
2198
+ "130324": {
2199
+ "content": "<unused_token_242>",
2200
+ "lstrip": false,
2201
+ "normalized": true,
2202
+ "rstrip": false,
2203
+ "single_word": false,
2204
+ "special": false
2205
+ },
2206
+ "130325": {
2207
+ "content": "<unused_token_243>",
2208
+ "lstrip": false,
2209
+ "normalized": true,
2210
+ "rstrip": false,
2211
+ "single_word": false,
2212
+ "special": false
2213
+ },
2214
+ "130326": {
2215
+ "content": "<unused_token_244>",
2216
+ "lstrip": false,
2217
+ "normalized": true,
2218
+ "rstrip": false,
2219
+ "single_word": false,
2220
+ "special": false
2221
+ },
2222
+ "130327": {
2223
+ "content": "<unused_token_245>",
2224
+ "lstrip": false,
2225
+ "normalized": true,
2226
+ "rstrip": false,
2227
+ "single_word": false,
2228
+ "special": false
2229
+ },
2230
+ "130328": {
2231
+ "content": "<unused_token_246>",
2232
+ "lstrip": false,
2233
+ "normalized": true,
2234
+ "rstrip": false,
2235
+ "single_word": false,
2236
+ "special": false
2237
+ },
2238
+ "130329": {
2239
+ "content": "<unused_token_247>",
2240
+ "lstrip": false,
2241
+ "normalized": true,
2242
+ "rstrip": false,
2243
+ "single_word": false,
2244
+ "special": false
2245
+ },
2246
+ "130330": {
2247
+ "content": "<unused_token_248>",
2248
+ "lstrip": false,
2249
+ "normalized": true,
2250
+ "rstrip": false,
2251
+ "single_word": false,
2252
+ "special": false
2253
+ },
2254
+ "130331": {
2255
+ "content": "<unused_token_249>",
2256
+ "lstrip": false,
2257
+ "normalized": true,
2258
+ "rstrip": false,
2259
+ "single_word": false,
2260
+ "special": false
2261
+ },
2262
+ "130332": {
2263
+ "content": "<unused_token_250>",
2264
+ "lstrip": false,
2265
+ "normalized": true,
2266
+ "rstrip": false,
2267
+ "single_word": false,
2268
+ "special": false
2269
+ },
2270
+ "130333": {
2271
+ "content": "<unused_token_251>",
2272
+ "lstrip": false,
2273
+ "normalized": true,
2274
+ "rstrip": false,
2275
+ "single_word": false,
2276
+ "special": false
2277
+ },
2278
+ "130334": {
2279
+ "content": "<unused_token_252>",
2280
+ "lstrip": false,
2281
+ "normalized": true,
2282
+ "rstrip": false,
2283
+ "single_word": false,
2284
+ "special": false
2285
+ },
2286
+ "130335": {
2287
+ "content": "<unused_token_253>",
2288
+ "lstrip": false,
2289
+ "normalized": true,
2290
+ "rstrip": false,
2291
+ "single_word": false,
2292
+ "special": false
2293
+ },
2294
+ "130336": {
2295
+ "content": "<unused_token_254>",
2296
+ "lstrip": false,
2297
+ "normalized": true,
2298
+ "rstrip": false,
2299
+ "single_word": false,
2300
+ "special": false
2301
+ },
2302
+ "130337": {
2303
+ "content": "<unused_token_255>",
2304
+ "lstrip": false,
2305
+ "normalized": true,
2306
+ "rstrip": false,
2307
+ "single_word": false,
2308
+ "special": false
2309
+ },
2310
+ "130338": {
2311
+ "content": "<unused_token_256>",
2312
+ "lstrip": false,
2313
+ "normalized": true,
2314
+ "rstrip": false,
2315
+ "single_word": false,
2316
+ "special": false
2317
+ },
2318
+ "130339": {
2319
+ "content": "<unused_token_257>",
2320
+ "lstrip": false,
2321
+ "normalized": true,
2322
+ "rstrip": false,
2323
+ "single_word": false,
2324
+ "special": false
2325
+ },
2326
+ "130340": {
2327
+ "content": "<unused_token_258>",
2328
+ "lstrip": false,
2329
+ "normalized": true,
2330
+ "rstrip": false,
2331
+ "single_word": false,
2332
+ "special": false
2333
+ },
2334
+ "130341": {
2335
+ "content": "<unused_token_259>",
2336
+ "lstrip": false,
2337
+ "normalized": true,
2338
+ "rstrip": false,
2339
+ "single_word": false,
2340
+ "special": false
2341
+ },
2342
+ "130342": {
2343
+ "content": "<unused_token_260>",
2344
+ "lstrip": false,
2345
+ "normalized": true,
2346
+ "rstrip": false,
2347
+ "single_word": false,
2348
+ "special": false
2349
+ },
2350
+ "130343": {
2351
+ "content": "<unused_token_261>",
2352
+ "lstrip": false,
2353
+ "normalized": true,
2354
+ "rstrip": false,
2355
+ "single_word": false,
2356
+ "special": false
2357
+ },
2358
+ "130344": {
2359
+ "content": "<unused_token_262>",
2360
+ "lstrip": false,
2361
+ "normalized": true,
2362
+ "rstrip": false,
2363
+ "single_word": false,
2364
+ "special": false
2365
+ },
2366
+ "130345": {
2367
+ "content": "<unused_token_263>",
2368
+ "lstrip": false,
2369
+ "normalized": true,
2370
+ "rstrip": false,
2371
+ "single_word": false,
2372
+ "special": false
2373
+ },
2374
+ "130346": {
2375
+ "content": "<unused_token_264>",
2376
+ "lstrip": false,
2377
+ "normalized": true,
2378
+ "rstrip": false,
2379
+ "single_word": false,
2380
+ "special": false
2381
+ },
2382
+ "130347": {
2383
+ "content": "<unused_token_265>",
2384
+ "lstrip": false,
2385
+ "normalized": true,
2386
+ "rstrip": false,
2387
+ "single_word": false,
2388
+ "special": false
2389
+ },
2390
+ "130348": {
2391
+ "content": "<unused_token_266>",
2392
+ "lstrip": false,
2393
+ "normalized": true,
2394
+ "rstrip": false,
2395
+ "single_word": false,
2396
+ "special": false
2397
+ },
2398
+ "130349": {
2399
+ "content": "<unused_token_267>",
2400
+ "lstrip": false,
2401
+ "normalized": true,
2402
+ "rstrip": false,
2403
+ "single_word": false,
2404
+ "special": false
2405
+ },
2406
+ "130350": {
2407
+ "content": "<unused_token_268>",
2408
+ "lstrip": false,
2409
+ "normalized": true,
2410
+ "rstrip": false,
2411
+ "single_word": false,
2412
+ "special": false
2413
+ },
2414
+ "130351": {
2415
+ "content": "<unused_token_269>",
2416
+ "lstrip": false,
2417
+ "normalized": true,
2418
+ "rstrip": false,
2419
+ "single_word": false,
2420
+ "special": false
2421
+ },
2422
+ "130352": {
2423
+ "content": "<unused_token_270>",
2424
+ "lstrip": false,
2425
+ "normalized": true,
2426
+ "rstrip": false,
2427
+ "single_word": false,
2428
+ "special": false
2429
+ },
2430
+ "130353": {
2431
+ "content": "<unused_token_271>",
2432
+ "lstrip": false,
2433
+ "normalized": true,
2434
+ "rstrip": false,
2435
+ "single_word": false,
2436
+ "special": false
2437
+ },
2438
+ "130354": {
2439
+ "content": "<unused_token_272>",
2440
+ "lstrip": false,
2441
+ "normalized": true,
2442
+ "rstrip": false,
2443
+ "single_word": false,
2444
+ "special": false
2445
+ },
2446
+ "130355": {
2447
+ "content": "<unused_token_273>",
2448
+ "lstrip": false,
2449
+ "normalized": true,
2450
+ "rstrip": false,
2451
+ "single_word": false,
2452
+ "special": false
2453
+ },
2454
+ "130356": {
2455
+ "content": "<unused_token_274>",
2456
+ "lstrip": false,
2457
+ "normalized": true,
2458
+ "rstrip": false,
2459
+ "single_word": false,
2460
+ "special": false
2461
+ },
2462
+ "130357": {
2463
+ "content": "<unused_token_275>",
2464
+ "lstrip": false,
2465
+ "normalized": true,
2466
+ "rstrip": false,
2467
+ "single_word": false,
2468
+ "special": false
2469
+ },
2470
+ "130358": {
2471
+ "content": "<unused_token_276>",
2472
+ "lstrip": false,
2473
+ "normalized": true,
2474
+ "rstrip": false,
2475
+ "single_word": false,
2476
+ "special": false
2477
+ },
2478
+ "130359": {
2479
+ "content": "<unused_token_277>",
2480
+ "lstrip": false,
2481
+ "normalized": true,
2482
+ "rstrip": false,
2483
+ "single_word": false,
2484
+ "special": false
2485
+ },
2486
+ "130360": {
2487
+ "content": "<unused_token_278>",
2488
+ "lstrip": false,
2489
+ "normalized": true,
2490
+ "rstrip": false,
2491
+ "single_word": false,
2492
+ "special": false
2493
+ },
2494
+ "130361": {
2495
+ "content": "<unused_token_279>",
2496
+ "lstrip": false,
2497
+ "normalized": true,
2498
+ "rstrip": false,
2499
+ "single_word": false,
2500
+ "special": false
2501
+ },
2502
+ "130362": {
2503
+ "content": "<unused_token_280>",
2504
+ "lstrip": false,
2505
+ "normalized": true,
2506
+ "rstrip": false,
2507
+ "single_word": false,
2508
+ "special": false
2509
+ },
2510
+ "130363": {
2511
+ "content": "<unused_token_281>",
2512
+ "lstrip": false,
2513
+ "normalized": true,
2514
+ "rstrip": false,
2515
+ "single_word": false,
2516
+ "special": false
2517
+ },
2518
+ "130364": {
2519
+ "content": "<unused_token_282>",
2520
+ "lstrip": false,
2521
+ "normalized": true,
2522
+ "rstrip": false,
2523
+ "single_word": false,
2524
+ "special": false
2525
+ },
2526
+ "130365": {
2527
+ "content": "<unused_token_283>",
2528
+ "lstrip": false,
2529
+ "normalized": true,
2530
+ "rstrip": false,
2531
+ "single_word": false,
2532
+ "special": false
2533
+ },
2534
+ "130366": {
2535
+ "content": "<unused_token_284>",
2536
+ "lstrip": false,
2537
+ "normalized": true,
2538
+ "rstrip": false,
2539
+ "single_word": false,
2540
+ "special": false
2541
+ },
2542
+ "130367": {
2543
+ "content": "<unused_token_285>",
2544
+ "lstrip": false,
2545
+ "normalized": true,
2546
+ "rstrip": false,
2547
+ "single_word": false,
2548
+ "special": false
2549
+ },
2550
+ "130368": {
2551
+ "content": "<unused_token_286>",
2552
+ "lstrip": false,
2553
+ "normalized": true,
2554
+ "rstrip": false,
2555
+ "single_word": false,
2556
+ "special": false
2557
+ },
2558
+ "130369": {
2559
+ "content": "<unused_token_287>",
2560
+ "lstrip": false,
2561
+ "normalized": true,
2562
+ "rstrip": false,
2563
+ "single_word": false,
2564
+ "special": false
2565
+ },
2566
+ "130370": {
2567
+ "content": "<unused_token_288>",
2568
+ "lstrip": false,
2569
+ "normalized": true,
2570
+ "rstrip": false,
2571
+ "single_word": false,
2572
+ "special": false
2573
+ },
2574
+ "130371": {
2575
+ "content": "<unused_token_289>",
2576
+ "lstrip": false,
2577
+ "normalized": true,
2578
+ "rstrip": false,
2579
+ "single_word": false,
2580
+ "special": false
2581
+ },
2582
+ "130372": {
2583
+ "content": "<unused_token_290>",
2584
+ "lstrip": false,
2585
+ "normalized": true,
2586
+ "rstrip": false,
2587
+ "single_word": false,
2588
+ "special": false
2589
+ },
2590
+ "130373": {
2591
+ "content": "<unused_token_291>",
2592
+ "lstrip": false,
2593
+ "normalized": true,
2594
+ "rstrip": false,
2595
+ "single_word": false,
2596
+ "special": false
2597
+ },
2598
+ "130374": {
2599
+ "content": "<unused_token_292>",
2600
+ "lstrip": false,
2601
+ "normalized": true,
2602
+ "rstrip": false,
2603
+ "single_word": false,
2604
+ "special": false
2605
+ },
2606
+ "130375": {
2607
+ "content": "<unused_token_293>",
2608
+ "lstrip": false,
2609
+ "normalized": true,
2610
+ "rstrip": false,
2611
+ "single_word": false,
2612
+ "special": false
2613
+ },
2614
+ "130376": {
2615
+ "content": "<unused_token_294>",
2616
+ "lstrip": false,
2617
+ "normalized": true,
2618
+ "rstrip": false,
2619
+ "single_word": false,
2620
+ "special": false
2621
+ },
2622
+ "130377": {
2623
+ "content": "<unused_token_295>",
2624
+ "lstrip": false,
2625
+ "normalized": true,
2626
+ "rstrip": false,
2627
+ "single_word": false,
2628
+ "special": false
2629
+ },
2630
+ "130378": {
2631
+ "content": "<unused_token_296>",
2632
+ "lstrip": false,
2633
+ "normalized": true,
2634
+ "rstrip": false,
2635
+ "single_word": false,
2636
+ "special": false
2637
+ },
2638
+ "130379": {
2639
+ "content": "<unused_token_297>",
2640
+ "lstrip": false,
2641
+ "normalized": true,
2642
+ "rstrip": false,
2643
+ "single_word": false,
2644
+ "special": false
2645
+ },
2646
+ "130380": {
2647
+ "content": "<unused_token_298>",
2648
+ "lstrip": false,
2649
+ "normalized": true,
2650
+ "rstrip": false,
2651
+ "single_word": false,
2652
+ "special": false
2653
+ },
2654
+ "130381": {
2655
+ "content": "<unused_token_299>",
2656
+ "lstrip": false,
2657
+ "normalized": true,
2658
+ "rstrip": false,
2659
+ "single_word": false,
2660
+ "special": false
2661
+ },
2662
+ "130382": {
2663
+ "content": "<unused_token_300>",
2664
+ "lstrip": false,
2665
+ "normalized": true,
2666
+ "rstrip": false,
2667
+ "single_word": false,
2668
+ "special": false
2669
+ },
2670
+ "130383": {
2671
+ "content": "<unused_token_301>",
2672
+ "lstrip": false,
2673
+ "normalized": true,
2674
+ "rstrip": false,
2675
+ "single_word": false,
2676
+ "special": false
2677
+ },
2678
+ "130384": {
2679
+ "content": "<unused_token_302>",
2680
+ "lstrip": false,
2681
+ "normalized": true,
2682
+ "rstrip": false,
2683
+ "single_word": false,
2684
+ "special": false
2685
+ },
2686
+ "130385": {
2687
+ "content": "<unused_token_303>",
2688
+ "lstrip": false,
2689
+ "normalized": true,
2690
+ "rstrip": false,
2691
+ "single_word": false,
2692
+ "special": false
2693
+ },
2694
+ "130386": {
2695
+ "content": "<unused_token_304>",
2696
+ "lstrip": false,
2697
+ "normalized": true,
2698
+ "rstrip": false,
2699
+ "single_word": false,
2700
+ "special": false
2701
+ },
2702
+ "130387": {
2703
+ "content": "<unused_token_305>",
2704
+ "lstrip": false,
2705
+ "normalized": true,
2706
+ "rstrip": false,
2707
+ "single_word": false,
2708
+ "special": false
2709
+ },
2710
+ "130388": {
2711
+ "content": "<unused_token_306>",
2712
+ "lstrip": false,
2713
+ "normalized": true,
2714
+ "rstrip": false,
2715
+ "single_word": false,
2716
+ "special": false
2717
+ },
2718
+ "130389": {
2719
+ "content": "<unused_token_307>",
2720
+ "lstrip": false,
2721
+ "normalized": true,
2722
+ "rstrip": false,
2723
+ "single_word": false,
2724
+ "special": false
2725
+ },
2726
+ "130390": {
2727
+ "content": "<unused_token_308>",
2728
+ "lstrip": false,
2729
+ "normalized": true,
2730
+ "rstrip": false,
2731
+ "single_word": false,
2732
+ "special": false
2733
+ },
2734
+ "130391": {
2735
+ "content": "<unused_token_309>",
2736
+ "lstrip": false,
2737
+ "normalized": true,
2738
+ "rstrip": false,
2739
+ "single_word": false,
2740
+ "special": false
2741
+ },
2742
+ "130392": {
2743
+ "content": "<unused_token_310>",
2744
+ "lstrip": false,
2745
+ "normalized": true,
2746
+ "rstrip": false,
2747
+ "single_word": false,
2748
+ "special": false
2749
+ },
2750
+ "130393": {
2751
+ "content": "<unused_token_311>",
2752
+ "lstrip": false,
2753
+ "normalized": true,
2754
+ "rstrip": false,
2755
+ "single_word": false,
2756
+ "special": false
2757
+ },
2758
+ "130394": {
2759
+ "content": "<unused_token_312>",
2760
+ "lstrip": false,
2761
+ "normalized": true,
2762
+ "rstrip": false,
2763
+ "single_word": false,
2764
+ "special": false
2765
+ },
2766
+ "130395": {
2767
+ "content": "<unused_token_313>",
2768
+ "lstrip": false,
2769
+ "normalized": true,
2770
+ "rstrip": false,
2771
+ "single_word": false,
2772
+ "special": false
2773
+ },
2774
+ "130396": {
2775
+ "content": "<unused_token_314>",
2776
+ "lstrip": false,
2777
+ "normalized": true,
2778
+ "rstrip": false,
2779
+ "single_word": false,
2780
+ "special": false
2781
+ },
2782
+ "130397": {
2783
+ "content": "<unused_token_315>",
2784
+ "lstrip": false,
2785
+ "normalized": true,
2786
+ "rstrip": false,
2787
+ "single_word": false,
2788
+ "special": false
2789
+ },
2790
+ "130398": {
2791
+ "content": "<unused_token_316>",
2792
+ "lstrip": false,
2793
+ "normalized": true,
2794
+ "rstrip": false,
2795
+ "single_word": false,
2796
+ "special": false
2797
+ },
2798
+ "130399": {
2799
+ "content": "<unused_token_317>",
2800
+ "lstrip": false,
2801
+ "normalized": true,
2802
+ "rstrip": false,
2803
+ "single_word": false,
2804
+ "special": false
2805
+ },
2806
+ "130400": {
2807
+ "content": "<unused_token_318>",
2808
+ "lstrip": false,
2809
+ "normalized": true,
2810
+ "rstrip": false,
2811
+ "single_word": false,
2812
+ "special": false
2813
+ },
2814
+ "130401": {
2815
+ "content": "<unused_token_319>",
2816
+ "lstrip": false,
2817
+ "normalized": true,
2818
+ "rstrip": false,
2819
+ "single_word": false,
2820
+ "special": false
2821
+ },
2822
+ "130402": {
2823
+ "content": "<unused_token_320>",
2824
+ "lstrip": false,
2825
+ "normalized": true,
2826
+ "rstrip": false,
2827
+ "single_word": false,
2828
+ "special": false
2829
+ },
2830
+ "130403": {
2831
+ "content": "<unused_token_321>",
2832
+ "lstrip": false,
2833
+ "normalized": true,
2834
+ "rstrip": false,
2835
+ "single_word": false,
2836
+ "special": false
2837
+ },
2838
+ "130404": {
2839
+ "content": "<unused_token_322>",
2840
+ "lstrip": false,
2841
+ "normalized": true,
2842
+ "rstrip": false,
2843
+ "single_word": false,
2844
+ "special": false
2845
+ },
2846
+ "130405": {
2847
+ "content": "<unused_token_323>",
2848
+ "lstrip": false,
2849
+ "normalized": true,
2850
+ "rstrip": false,
2851
+ "single_word": false,
2852
+ "special": false
2853
+ },
2854
+ "130406": {
2855
+ "content": "<unused_token_324>",
2856
+ "lstrip": false,
2857
+ "normalized": true,
2858
+ "rstrip": false,
2859
+ "single_word": false,
2860
+ "special": false
2861
+ },
2862
+ "130407": {
2863
+ "content": "<unused_token_325>",
2864
+ "lstrip": false,
2865
+ "normalized": true,
2866
+ "rstrip": false,
2867
+ "single_word": false,
2868
+ "special": false
2869
+ },
2870
+ "130408": {
2871
+ "content": "<unused_token_326>",
2872
+ "lstrip": false,
2873
+ "normalized": true,
2874
+ "rstrip": false,
2875
+ "single_word": false,
2876
+ "special": false
2877
+ },
2878
+ "130409": {
2879
+ "content": "<unused_token_327>",
2880
+ "lstrip": false,
2881
+ "normalized": true,
2882
+ "rstrip": false,
2883
+ "single_word": false,
2884
+ "special": false
2885
+ },
2886
+ "130410": {
2887
+ "content": "<unused_token_328>",
2888
+ "lstrip": false,
2889
+ "normalized": true,
2890
+ "rstrip": false,
2891
+ "single_word": false,
2892
+ "special": false
2893
+ },
2894
+ "130411": {
2895
+ "content": "<unused_token_329>",
2896
+ "lstrip": false,
2897
+ "normalized": true,
2898
+ "rstrip": false,
2899
+ "single_word": false,
2900
+ "special": false
2901
+ },
2902
+ "130412": {
2903
+ "content": "<unused_token_330>",
2904
+ "lstrip": false,
2905
+ "normalized": true,
2906
+ "rstrip": false,
2907
+ "single_word": false,
2908
+ "special": false
2909
+ },
2910
+ "130413": {
2911
+ "content": "<unused_token_331>",
2912
+ "lstrip": false,
2913
+ "normalized": true,
2914
+ "rstrip": false,
2915
+ "single_word": false,
2916
+ "special": false
2917
+ },
2918
+ "130414": {
2919
+ "content": "<unused_token_332>",
2920
+ "lstrip": false,
2921
+ "normalized": true,
2922
+ "rstrip": false,
2923
+ "single_word": false,
2924
+ "special": false
2925
+ },
2926
+ "130415": {
2927
+ "content": "<unused_token_333>",
2928
+ "lstrip": false,
2929
+ "normalized": true,
2930
+ "rstrip": false,
2931
+ "single_word": false,
2932
+ "special": false
2933
+ },
2934
+ "130416": {
2935
+ "content": "<unused_token_334>",
2936
+ "lstrip": false,
2937
+ "normalized": true,
2938
+ "rstrip": false,
2939
+ "single_word": false,
2940
+ "special": false
2941
+ },
2942
+ "130417": {
2943
+ "content": "<unused_token_335>",
2944
+ "lstrip": false,
2945
+ "normalized": true,
2946
+ "rstrip": false,
2947
+ "single_word": false,
2948
+ "special": false
2949
+ },
2950
+ "130418": {
2951
+ "content": "<unused_token_336>",
2952
+ "lstrip": false,
2953
+ "normalized": true,
2954
+ "rstrip": false,
2955
+ "single_word": false,
2956
+ "special": false
2957
+ },
2958
+ "130419": {
2959
+ "content": "<unused_token_337>",
2960
+ "lstrip": false,
2961
+ "normalized": true,
2962
+ "rstrip": false,
2963
+ "single_word": false,
2964
+ "special": false
2965
+ },
2966
+ "130420": {
2967
+ "content": "<unused_token_338>",
2968
+ "lstrip": false,
2969
+ "normalized": true,
2970
+ "rstrip": false,
2971
+ "single_word": false,
2972
+ "special": false
2973
+ },
2974
+ "130421": {
2975
+ "content": "<unused_token_339>",
2976
+ "lstrip": false,
2977
+ "normalized": true,
2978
+ "rstrip": false,
2979
+ "single_word": false,
2980
+ "special": false
2981
+ },
2982
+ "130422": {
2983
+ "content": "<unused_token_340>",
2984
+ "lstrip": false,
2985
+ "normalized": true,
2986
+ "rstrip": false,
2987
+ "single_word": false,
2988
+ "special": false
2989
+ },
2990
+ "130423": {
2991
+ "content": "<unused_token_341>",
2992
+ "lstrip": false,
2993
+ "normalized": true,
2994
+ "rstrip": false,
2995
+ "single_word": false,
2996
+ "special": false
2997
+ },
2998
+ "130424": {
2999
+ "content": "<unused_token_342>",
3000
+ "lstrip": false,
3001
+ "normalized": true,
3002
+ "rstrip": false,
3003
+ "single_word": false,
3004
+ "special": false
3005
+ },
3006
+ "130425": {
3007
+ "content": "<unused_token_343>",
3008
+ "lstrip": false,
3009
+ "normalized": true,
3010
+ "rstrip": false,
3011
+ "single_word": false,
3012
+ "special": false
3013
+ },
3014
+ "130426": {
3015
+ "content": "<unused_token_344>",
3016
+ "lstrip": false,
3017
+ "normalized": true,
3018
+ "rstrip": false,
3019
+ "single_word": false,
3020
+ "special": false
3021
+ },
3022
+ "130427": {
3023
+ "content": "<unused_token_345>",
3024
+ "lstrip": false,
3025
+ "normalized": true,
3026
+ "rstrip": false,
3027
+ "single_word": false,
3028
+ "special": false
3029
+ },
3030
+ "130428": {
3031
+ "content": "<unused_token_346>",
3032
+ "lstrip": false,
3033
+ "normalized": true,
3034
+ "rstrip": false,
3035
+ "single_word": false,
3036
+ "special": false
3037
+ },
3038
+ "130429": {
3039
+ "content": "<unused_token_347>",
3040
+ "lstrip": false,
3041
+ "normalized": true,
3042
+ "rstrip": false,
3043
+ "single_word": false,
3044
+ "special": false
3045
+ },
3046
+ "130430": {
3047
+ "content": "<unused_token_348>",
3048
+ "lstrip": false,
3049
+ "normalized": true,
3050
+ "rstrip": false,
3051
+ "single_word": false,
3052
+ "special": false
3053
+ },
3054
+ "130431": {
3055
+ "content": "<unused_token_349>",
3056
+ "lstrip": false,
3057
+ "normalized": true,
3058
+ "rstrip": false,
3059
+ "single_word": false,
3060
+ "special": false
3061
+ },
3062
+ "130432": {
3063
+ "content": "<unused_token_350>",
3064
+ "lstrip": false,
3065
+ "normalized": true,
3066
+ "rstrip": false,
3067
+ "single_word": false,
3068
+ "special": false
3069
+ },
3070
+ "130433": {
3071
+ "content": "<unused_token_351>",
3072
+ "lstrip": false,
3073
+ "normalized": true,
3074
+ "rstrip": false,
3075
+ "single_word": false,
3076
+ "special": false
3077
+ },
3078
+ "130434": {
3079
+ "content": "<unused_token_352>",
3080
+ "lstrip": false,
3081
+ "normalized": true,
3082
+ "rstrip": false,
3083
+ "single_word": false,
3084
+ "special": false
3085
+ },
3086
+ "130435": {
3087
+ "content": "<unused_token_353>",
3088
+ "lstrip": false,
3089
+ "normalized": true,
3090
+ "rstrip": false,
3091
+ "single_word": false,
3092
+ "special": false
3093
+ },
3094
+ "130436": {
3095
+ "content": "<unused_token_354>",
3096
+ "lstrip": false,
3097
+ "normalized": true,
3098
+ "rstrip": false,
3099
+ "single_word": false,
3100
+ "special": false
3101
+ },
3102
+ "130437": {
3103
+ "content": "<unused_token_355>",
3104
+ "lstrip": false,
3105
+ "normalized": true,
3106
+ "rstrip": false,
3107
+ "single_word": false,
3108
+ "special": false
3109
+ },
3110
+ "130438": {
3111
+ "content": "<unused_token_356>",
3112
+ "lstrip": false,
3113
+ "normalized": true,
3114
+ "rstrip": false,
3115
+ "single_word": false,
3116
+ "special": false
3117
+ },
3118
+ "130439": {
3119
+ "content": "<unused_token_357>",
3120
+ "lstrip": false,
3121
+ "normalized": true,
3122
+ "rstrip": false,
3123
+ "single_word": false,
3124
+ "special": false
3125
+ },
3126
+ "130440": {
3127
+ "content": "<unused_token_358>",
3128
+ "lstrip": false,
3129
+ "normalized": true,
3130
+ "rstrip": false,
3131
+ "single_word": false,
3132
+ "special": false
3133
+ },
3134
+ "130441": {
3135
+ "content": "<unused_token_359>",
3136
+ "lstrip": false,
3137
+ "normalized": true,
3138
+ "rstrip": false,
3139
+ "single_word": false,
3140
+ "special": false
3141
+ },
3142
+ "130442": {
3143
+ "content": "<unused_token_360>",
3144
+ "lstrip": false,
3145
+ "normalized": true,
3146
+ "rstrip": false,
3147
+ "single_word": false,
3148
+ "special": false
3149
+ },
3150
+ "130443": {
3151
+ "content": "<unused_token_361>",
3152
+ "lstrip": false,
3153
+ "normalized": true,
3154
+ "rstrip": false,
3155
+ "single_word": false,
3156
+ "special": false
3157
+ },
3158
+ "130444": {
3159
+ "content": "<unused_token_362>",
3160
+ "lstrip": false,
3161
+ "normalized": true,
3162
+ "rstrip": false,
3163
+ "single_word": false,
3164
+ "special": false
3165
+ },
3166
+ "130445": {
3167
+ "content": "<unused_token_363>",
3168
+ "lstrip": false,
3169
+ "normalized": true,
3170
+ "rstrip": false,
3171
+ "single_word": false,
3172
+ "special": false
3173
+ },
3174
+ "130446": {
3175
+ "content": "<unused_token_364>",
3176
+ "lstrip": false,
3177
+ "normalized": true,
3178
+ "rstrip": false,
3179
+ "single_word": false,
3180
+ "special": false
3181
+ },
3182
+ "130447": {
3183
+ "content": "<unused_token_365>",
3184
+ "lstrip": false,
3185
+ "normalized": true,
3186
+ "rstrip": false,
3187
+ "single_word": false,
3188
+ "special": false
3189
+ },
3190
+ "130448": {
3191
+ "content": "<unused_token_366>",
3192
+ "lstrip": false,
3193
+ "normalized": true,
3194
+ "rstrip": false,
3195
+ "single_word": false,
3196
+ "special": false
3197
+ },
3198
+ "130449": {
3199
+ "content": "<unused_token_367>",
3200
+ "lstrip": false,
3201
+ "normalized": true,
3202
+ "rstrip": false,
3203
+ "single_word": false,
3204
+ "special": false
3205
+ },
3206
+ "130450": {
3207
+ "content": "<unused_token_368>",
3208
+ "lstrip": false,
3209
+ "normalized": true,
3210
+ "rstrip": false,
3211
+ "single_word": false,
3212
+ "special": false
3213
+ },
3214
+ "130451": {
3215
+ "content": "<unused_token_369>",
3216
+ "lstrip": false,
3217
+ "normalized": true,
3218
+ "rstrip": false,
3219
+ "single_word": false,
3220
+ "special": false
3221
+ },
3222
+ "130452": {
3223
+ "content": "<unused_token_370>",
3224
+ "lstrip": false,
3225
+ "normalized": true,
3226
+ "rstrip": false,
3227
+ "single_word": false,
3228
+ "special": false
3229
+ },
3230
+ "130453": {
3231
+ "content": "<unused_token_371>",
3232
+ "lstrip": false,
3233
+ "normalized": true,
3234
+ "rstrip": false,
3235
+ "single_word": false,
3236
+ "special": false
3237
+ },
3238
+ "130454": {
3239
+ "content": "<unused_token_372>",
3240
+ "lstrip": false,
3241
+ "normalized": true,
3242
+ "rstrip": false,
3243
+ "single_word": false,
3244
+ "special": false
3245
+ },
3246
+ "130455": {
3247
+ "content": "<unused_token_373>",
3248
+ "lstrip": false,
3249
+ "normalized": true,
3250
+ "rstrip": false,
3251
+ "single_word": false,
3252
+ "special": false
3253
+ },
3254
+ "130456": {
3255
+ "content": "<unused_token_374>",
3256
+ "lstrip": false,
3257
+ "normalized": true,
3258
+ "rstrip": false,
3259
+ "single_word": false,
3260
+ "special": false
3261
+ },
3262
+ "130457": {
3263
+ "content": "<unused_token_375>",
3264
+ "lstrip": false,
3265
+ "normalized": true,
3266
+ "rstrip": false,
3267
+ "single_word": false,
3268
+ "special": false
3269
+ },
3270
+ "130458": {
3271
+ "content": "<unused_token_376>",
3272
+ "lstrip": false,
3273
+ "normalized": true,
3274
+ "rstrip": false,
3275
+ "single_word": false,
3276
+ "special": false
3277
+ },
3278
+ "130459": {
3279
+ "content": "<unused_token_377>",
3280
+ "lstrip": false,
3281
+ "normalized": true,
3282
+ "rstrip": false,
3283
+ "single_word": false,
3284
+ "special": false
3285
+ },
3286
+ "130460": {
3287
+ "content": "<unused_token_378>",
3288
+ "lstrip": false,
3289
+ "normalized": true,
3290
+ "rstrip": false,
3291
+ "single_word": false,
3292
+ "special": false
3293
+ },
3294
+ "130461": {
3295
+ "content": "<unused_token_379>",
3296
+ "lstrip": false,
3297
+ "normalized": true,
3298
+ "rstrip": false,
3299
+ "single_word": false,
3300
+ "special": false
3301
+ },
3302
+ "130462": {
3303
+ "content": "<unused_token_380>",
3304
+ "lstrip": false,
3305
+ "normalized": true,
3306
+ "rstrip": false,
3307
+ "single_word": false,
3308
+ "special": false
3309
+ },
3310
+ "130463": {
3311
+ "content": "<unused_token_381>",
3312
+ "lstrip": false,
3313
+ "normalized": true,
3314
+ "rstrip": false,
3315
+ "single_word": false,
3316
+ "special": false
3317
+ },
3318
+ "130464": {
3319
+ "content": "<unused_token_382>",
3320
+ "lstrip": false,
3321
+ "normalized": true,
3322
+ "rstrip": false,
3323
+ "single_word": false,
3324
+ "special": false
3325
+ },
3326
+ "130465": {
3327
+ "content": "<unused_token_383>",
3328
+ "lstrip": false,
3329
+ "normalized": true,
3330
+ "rstrip": false,
3331
+ "single_word": false,
3332
+ "special": false
3333
+ },
3334
+ "130466": {
3335
+ "content": "<unused_token_384>",
3336
+ "lstrip": false,
3337
+ "normalized": true,
3338
+ "rstrip": false,
3339
+ "single_word": false,
3340
+ "special": false
3341
+ },
3342
+ "130467": {
3343
+ "content": "<unused_token_385>",
3344
+ "lstrip": false,
3345
+ "normalized": true,
3346
+ "rstrip": false,
3347
+ "single_word": false,
3348
+ "special": false
3349
+ },
3350
+ "130468": {
3351
+ "content": "<unused_token_386>",
3352
+ "lstrip": false,
3353
+ "normalized": true,
3354
+ "rstrip": false,
3355
+ "single_word": false,
3356
+ "special": false
3357
+ },
3358
+ "130469": {
3359
+ "content": "<unused_token_387>",
3360
+ "lstrip": false,
3361
+ "normalized": true,
3362
+ "rstrip": false,
3363
+ "single_word": false,
3364
+ "special": false
3365
+ },
3366
+ "130470": {
3367
+ "content": "<unused_token_388>",
3368
+ "lstrip": false,
3369
+ "normalized": true,
3370
+ "rstrip": false,
3371
+ "single_word": false,
3372
+ "special": false
3373
+ },
3374
+ "130471": {
3375
+ "content": "<unused_token_389>",
3376
+ "lstrip": false,
3377
+ "normalized": true,
3378
+ "rstrip": false,
3379
+ "single_word": false,
3380
+ "special": false
3381
+ },
3382
+ "130472": {
3383
+ "content": "<unused_token_390>",
3384
+ "lstrip": false,
3385
+ "normalized": true,
3386
+ "rstrip": false,
3387
+ "single_word": false,
3388
+ "special": false
3389
+ },
3390
+ "130473": {
3391
+ "content": "<unused_token_391>",
3392
+ "lstrip": false,
3393
+ "normalized": true,
3394
+ "rstrip": false,
3395
+ "single_word": false,
3396
+ "special": false
3397
+ },
3398
+ "130474": {
3399
+ "content": "<unused_token_392>",
3400
+ "lstrip": false,
3401
+ "normalized": true,
3402
+ "rstrip": false,
3403
+ "single_word": false,
3404
+ "special": false
3405
+ },
3406
+ "130475": {
3407
+ "content": "<unused_token_393>",
3408
+ "lstrip": false,
3409
+ "normalized": true,
3410
+ "rstrip": false,
3411
+ "single_word": false,
3412
+ "special": false
3413
+ },
3414
+ "130476": {
3415
+ "content": "<unused_token_394>",
3416
+ "lstrip": false,
3417
+ "normalized": true,
3418
+ "rstrip": false,
3419
+ "single_word": false,
3420
+ "special": false
3421
+ },
3422
+ "130477": {
3423
+ "content": "<unused_token_395>",
3424
+ "lstrip": false,
3425
+ "normalized": true,
3426
+ "rstrip": false,
3427
+ "single_word": false,
3428
+ "special": false
3429
+ },
3430
+ "130478": {
3431
+ "content": "<unused_token_396>",
3432
+ "lstrip": false,
3433
+ "normalized": true,
3434
+ "rstrip": false,
3435
+ "single_word": false,
3436
+ "special": false
3437
+ },
3438
+ "130479": {
3439
+ "content": "<unused_token_397>",
3440
+ "lstrip": false,
3441
+ "normalized": true,
3442
+ "rstrip": false,
3443
+ "single_word": false,
3444
+ "special": false
3445
+ },
3446
+ "130480": {
3447
+ "content": "<unused_token_398>",
3448
+ "lstrip": false,
3449
+ "normalized": true,
3450
+ "rstrip": false,
3451
+ "single_word": false,
3452
+ "special": false
3453
+ },
3454
+ "130481": {
3455
+ "content": "<unused_token_399>",
3456
+ "lstrip": false,
3457
+ "normalized": true,
3458
+ "rstrip": false,
3459
+ "single_word": false,
3460
+ "special": false
3461
+ },
3462
+ "130482": {
3463
+ "content": "<unused_token_400>",
3464
+ "lstrip": false,
3465
+ "normalized": true,
3466
+ "rstrip": false,
3467
+ "single_word": false,
3468
+ "special": false
3469
+ },
3470
+ "130483": {
3471
+ "content": "<unused_token_401>",
3472
+ "lstrip": false,
3473
+ "normalized": true,
3474
+ "rstrip": false,
3475
+ "single_word": false,
3476
+ "special": false
3477
+ },
3478
+ "130484": {
3479
+ "content": "<unused_token_402>",
3480
+ "lstrip": false,
3481
+ "normalized": true,
3482
+ "rstrip": false,
3483
+ "single_word": false,
3484
+ "special": false
3485
+ },
3486
+ "130485": {
3487
+ "content": "<unused_token_403>",
3488
+ "lstrip": false,
3489
+ "normalized": true,
3490
+ "rstrip": false,
3491
+ "single_word": false,
3492
+ "special": false
3493
+ },
3494
+ "130486": {
3495
+ "content": "<unused_token_404>",
3496
+ "lstrip": false,
3497
+ "normalized": true,
3498
+ "rstrip": false,
3499
+ "single_word": false,
3500
+ "special": false
3501
+ },
3502
+ "130487": {
3503
+ "content": "<unused_token_405>",
3504
+ "lstrip": false,
3505
+ "normalized": true,
3506
+ "rstrip": false,
3507
+ "single_word": false,
3508
+ "special": false
3509
+ },
3510
+ "130488": {
3511
+ "content": "<unused_token_406>",
3512
+ "lstrip": false,
3513
+ "normalized": true,
3514
+ "rstrip": false,
3515
+ "single_word": false,
3516
+ "special": false
3517
+ },
3518
+ "130489": {
3519
+ "content": "<unused_token_407>",
3520
+ "lstrip": false,
3521
+ "normalized": true,
3522
+ "rstrip": false,
3523
+ "single_word": false,
3524
+ "special": false
3525
+ },
3526
+ "130490": {
3527
+ "content": "<unused_token_408>",
3528
+ "lstrip": false,
3529
+ "normalized": true,
3530
+ "rstrip": false,
3531
+ "single_word": false,
3532
+ "special": false
3533
+ },
3534
+ "130491": {
3535
+ "content": "<unused_token_409>",
3536
+ "lstrip": false,
3537
+ "normalized": true,
3538
+ "rstrip": false,
3539
+ "single_word": false,
3540
+ "special": false
3541
+ },
3542
+ "130492": {
3543
+ "content": "<unused_token_410>",
3544
+ "lstrip": false,
3545
+ "normalized": true,
3546
+ "rstrip": false,
3547
+ "single_word": false,
3548
+ "special": false
3549
+ },
3550
+ "130493": {
3551
+ "content": "<unused_token_411>",
3552
+ "lstrip": false,
3553
+ "normalized": true,
3554
+ "rstrip": false,
3555
+ "single_word": false,
3556
+ "special": false
3557
+ },
3558
+ "130494": {
3559
+ "content": "<unused_token_412>",
3560
+ "lstrip": false,
3561
+ "normalized": true,
3562
+ "rstrip": false,
3563
+ "single_word": false,
3564
+ "special": false
3565
+ },
3566
+ "130495": {
3567
+ "content": "<unused_token_413>",
3568
+ "lstrip": false,
3569
+ "normalized": true,
3570
+ "rstrip": false,
3571
+ "single_word": false,
3572
+ "special": false
3573
+ },
3574
+ "130496": {
3575
+ "content": "<unused_token_414>",
3576
+ "lstrip": false,
3577
+ "normalized": true,
3578
+ "rstrip": false,
3579
+ "single_word": false,
3580
+ "special": false
3581
+ },
3582
+ "130497": {
3583
+ "content": "<unused_token_415>",
3584
+ "lstrip": false,
3585
+ "normalized": true,
3586
+ "rstrip": false,
3587
+ "single_word": false,
3588
+ "special": false
3589
+ },
3590
+ "130498": {
3591
+ "content": "<unused_token_416>",
3592
+ "lstrip": false,
3593
+ "normalized": true,
3594
+ "rstrip": false,
3595
+ "single_word": false,
3596
+ "special": false
3597
+ },
3598
+ "130499": {
3599
+ "content": "<unused_token_417>",
3600
+ "lstrip": false,
3601
+ "normalized": true,
3602
+ "rstrip": false,
3603
+ "single_word": false,
3604
+ "special": false
3605
+ },
3606
+ "130500": {
3607
+ "content": "<unused_token_418>",
3608
+ "lstrip": false,
3609
+ "normalized": true,
3610
+ "rstrip": false,
3611
+ "single_word": false,
3612
+ "special": false
3613
+ },
3614
+ "130501": {
3615
+ "content": "<unused_token_419>",
3616
+ "lstrip": false,
3617
+ "normalized": true,
3618
+ "rstrip": false,
3619
+ "single_word": false,
3620
+ "special": false
3621
+ },
3622
+ "130502": {
3623
+ "content": "<unused_token_420>",
3624
+ "lstrip": false,
3625
+ "normalized": true,
3626
+ "rstrip": false,
3627
+ "single_word": false,
3628
+ "special": false
3629
+ },
3630
+ "130503": {
3631
+ "content": "<unused_token_421>",
3632
+ "lstrip": false,
3633
+ "normalized": true,
3634
+ "rstrip": false,
3635
+ "single_word": false,
3636
+ "special": false
3637
+ },
3638
+ "130504": {
3639
+ "content": "<unused_token_422>",
3640
+ "lstrip": false,
3641
+ "normalized": true,
3642
+ "rstrip": false,
3643
+ "single_word": false,
3644
+ "special": false
3645
+ },
3646
+ "130505": {
3647
+ "content": "<unused_token_423>",
3648
+ "lstrip": false,
3649
+ "normalized": true,
3650
+ "rstrip": false,
3651
+ "single_word": false,
3652
+ "special": false
3653
+ },
3654
+ "130506": {
3655
+ "content": "<unused_token_424>",
3656
+ "lstrip": false,
3657
+ "normalized": true,
3658
+ "rstrip": false,
3659
+ "single_word": false,
3660
+ "special": false
3661
+ },
3662
+ "130507": {
3663
+ "content": "<unused_token_425>",
3664
+ "lstrip": false,
3665
+ "normalized": true,
3666
+ "rstrip": false,
3667
+ "single_word": false,
3668
+ "special": false
3669
+ },
3670
+ "130508": {
3671
+ "content": "<unused_token_426>",
3672
+ "lstrip": false,
3673
+ "normalized": true,
3674
+ "rstrip": false,
3675
+ "single_word": false,
3676
+ "special": false
3677
+ },
3678
+ "130509": {
3679
+ "content": "<unused_token_427>",
3680
+ "lstrip": false,
3681
+ "normalized": true,
3682
+ "rstrip": false,
3683
+ "single_word": false,
3684
+ "special": false
3685
+ },
3686
+ "130510": {
3687
+ "content": "<unused_token_428>",
3688
+ "lstrip": false,
3689
+ "normalized": true,
3690
+ "rstrip": false,
3691
+ "single_word": false,
3692
+ "special": false
3693
+ },
3694
+ "130511": {
3695
+ "content": "<unused_token_429>",
3696
+ "lstrip": false,
3697
+ "normalized": true,
3698
+ "rstrip": false,
3699
+ "single_word": false,
3700
+ "special": false
3701
+ },
3702
+ "130512": {
3703
+ "content": "<unused_token_430>",
3704
+ "lstrip": false,
3705
+ "normalized": true,
3706
+ "rstrip": false,
3707
+ "single_word": false,
3708
+ "special": false
3709
+ },
3710
+ "130513": {
3711
+ "content": "<unused_token_431>",
3712
+ "lstrip": false,
3713
+ "normalized": true,
3714
+ "rstrip": false,
3715
+ "single_word": false,
3716
+ "special": false
3717
+ },
3718
+ "130514": {
3719
+ "content": "<unused_token_432>",
3720
+ "lstrip": false,
3721
+ "normalized": true,
3722
+ "rstrip": false,
3723
+ "single_word": false,
3724
+ "special": false
3725
+ },
3726
+ "130515": {
3727
+ "content": "<unused_token_433>",
3728
+ "lstrip": false,
3729
+ "normalized": true,
3730
+ "rstrip": false,
3731
+ "single_word": false,
3732
+ "special": false
3733
+ },
3734
+ "130516": {
3735
+ "content": "<unused_token_434>",
3736
+ "lstrip": false,
3737
+ "normalized": true,
3738
+ "rstrip": false,
3739
+ "single_word": false,
3740
+ "special": false
3741
+ },
3742
+ "130517": {
3743
+ "content": "<unused_token_435>",
3744
+ "lstrip": false,
3745
+ "normalized": true,
3746
+ "rstrip": false,
3747
+ "single_word": false,
3748
+ "special": false
3749
+ },
3750
+ "130518": {
3751
+ "content": "<unused_token_436>",
3752
+ "lstrip": false,
3753
+ "normalized": true,
3754
+ "rstrip": false,
3755
+ "single_word": false,
3756
+ "special": false
3757
+ },
3758
+ "130519": {
3759
+ "content": "<unused_token_437>",
3760
+ "lstrip": false,
3761
+ "normalized": true,
3762
+ "rstrip": false,
3763
+ "single_word": false,
3764
+ "special": false
3765
+ },
3766
+ "130520": {
3767
+ "content": "<unused_token_438>",
3768
+ "lstrip": false,
3769
+ "normalized": true,
3770
+ "rstrip": false,
3771
+ "single_word": false,
3772
+ "special": false
3773
+ },
3774
+ "130521": {
3775
+ "content": "<unused_token_439>",
3776
+ "lstrip": false,
3777
+ "normalized": true,
3778
+ "rstrip": false,
3779
+ "single_word": false,
3780
+ "special": false
3781
+ },
3782
+ "130522": {
3783
+ "content": "<unused_token_440>",
3784
+ "lstrip": false,
3785
+ "normalized": true,
3786
+ "rstrip": false,
3787
+ "single_word": false,
3788
+ "special": false
3789
+ },
3790
+ "130523": {
3791
+ "content": "<unused_token_441>",
3792
+ "lstrip": false,
3793
+ "normalized": true,
3794
+ "rstrip": false,
3795
+ "single_word": false,
3796
+ "special": false
3797
+ },
3798
+ "130524": {
3799
+ "content": "<unused_token_442>",
3800
+ "lstrip": false,
3801
+ "normalized": true,
3802
+ "rstrip": false,
3803
+ "single_word": false,
3804
+ "special": false
3805
+ },
3806
+ "130525": {
3807
+ "content": "<unused_token_443>",
3808
+ "lstrip": false,
3809
+ "normalized": true,
3810
+ "rstrip": false,
3811
+ "single_word": false,
3812
+ "special": false
3813
+ },
3814
+ "130526": {
3815
+ "content": "<unused_token_444>",
3816
+ "lstrip": false,
3817
+ "normalized": true,
3818
+ "rstrip": false,
3819
+ "single_word": false,
3820
+ "special": false
3821
+ },
3822
+ "130527": {
3823
+ "content": "<unused_token_445>",
3824
+ "lstrip": false,
3825
+ "normalized": true,
3826
+ "rstrip": false,
3827
+ "single_word": false,
3828
+ "special": false
3829
+ },
3830
+ "130528": {
3831
+ "content": "<unused_token_446>",
3832
+ "lstrip": false,
3833
+ "normalized": true,
3834
+ "rstrip": false,
3835
+ "single_word": false,
3836
+ "special": false
3837
+ },
3838
+ "130529": {
3839
+ "content": "<unused_token_447>",
3840
+ "lstrip": false,
3841
+ "normalized": true,
3842
+ "rstrip": false,
3843
+ "single_word": false,
3844
+ "special": false
3845
+ },
3846
+ "130530": {
3847
+ "content": "<unused_token_448>",
3848
+ "lstrip": false,
3849
+ "normalized": true,
3850
+ "rstrip": false,
3851
+ "single_word": false,
3852
+ "special": false
3853
+ },
3854
+ "130531": {
3855
+ "content": "<unused_token_449>",
3856
+ "lstrip": false,
3857
+ "normalized": true,
3858
+ "rstrip": false,
3859
+ "single_word": false,
3860
+ "special": false
3861
+ },
3862
+ "130532": {
3863
+ "content": "<unused_token_450>",
3864
+ "lstrip": false,
3865
+ "normalized": true,
3866
+ "rstrip": false,
3867
+ "single_word": false,
3868
+ "special": false
3869
+ },
3870
+ "130533": {
3871
+ "content": "<unused_token_451>",
3872
+ "lstrip": false,
3873
+ "normalized": true,
3874
+ "rstrip": false,
3875
+ "single_word": false,
3876
+ "special": false
3877
+ },
3878
+ "130534": {
3879
+ "content": "<unused_token_452>",
3880
+ "lstrip": false,
3881
+ "normalized": true,
3882
+ "rstrip": false,
3883
+ "single_word": false,
3884
+ "special": false
3885
+ },
3886
+ "130535": {
3887
+ "content": "<unused_token_453>",
3888
+ "lstrip": false,
3889
+ "normalized": true,
3890
+ "rstrip": false,
3891
+ "single_word": false,
3892
+ "special": false
3893
+ },
3894
+ "130536": {
3895
+ "content": "<unused_token_454>",
3896
+ "lstrip": false,
3897
+ "normalized": true,
3898
+ "rstrip": false,
3899
+ "single_word": false,
3900
+ "special": false
3901
+ },
3902
+ "130537": {
3903
+ "content": "<unused_token_455>",
3904
+ "lstrip": false,
3905
+ "normalized": true,
3906
+ "rstrip": false,
3907
+ "single_word": false,
3908
+ "special": false
3909
+ },
3910
+ "130538": {
3911
+ "content": "<unused_token_456>",
3912
+ "lstrip": false,
3913
+ "normalized": true,
3914
+ "rstrip": false,
3915
+ "single_word": false,
3916
+ "special": false
3917
+ },
3918
+ "130539": {
3919
+ "content": "<unused_token_457>",
3920
+ "lstrip": false,
3921
+ "normalized": true,
3922
+ "rstrip": false,
3923
+ "single_word": false,
3924
+ "special": false
3925
+ },
3926
+ "130540": {
3927
+ "content": "<unused_token_458>",
3928
+ "lstrip": false,
3929
+ "normalized": true,
3930
+ "rstrip": false,
3931
+ "single_word": false,
3932
+ "special": false
3933
+ },
3934
+ "130541": {
3935
+ "content": "<unused_token_459>",
3936
+ "lstrip": false,
3937
+ "normalized": true,
3938
+ "rstrip": false,
3939
+ "single_word": false,
3940
+ "special": false
3941
+ },
3942
+ "130542": {
3943
+ "content": "<unused_token_460>",
3944
+ "lstrip": false,
3945
+ "normalized": true,
3946
+ "rstrip": false,
3947
+ "single_word": false,
3948
+ "special": false
3949
+ },
3950
+ "130543": {
3951
+ "content": "<unused_token_461>",
3952
+ "lstrip": false,
3953
+ "normalized": true,
3954
+ "rstrip": false,
3955
+ "single_word": false,
3956
+ "special": false
3957
+ },
3958
+ "130544": {
3959
+ "content": "<unused_token_462>",
3960
+ "lstrip": false,
3961
+ "normalized": true,
3962
+ "rstrip": false,
3963
+ "single_word": false,
3964
+ "special": false
3965
+ },
3966
+ "130545": {
3967
+ "content": "<unused_token_463>",
3968
+ "lstrip": false,
3969
+ "normalized": true,
3970
+ "rstrip": false,
3971
+ "single_word": false,
3972
+ "special": false
3973
+ },
3974
+ "130546": {
3975
+ "content": "<unused_token_464>",
3976
+ "lstrip": false,
3977
+ "normalized": true,
3978
+ "rstrip": false,
3979
+ "single_word": false,
3980
+ "special": false
3981
+ },
3982
+ "130547": {
3983
+ "content": "<unused_token_465>",
3984
+ "lstrip": false,
3985
+ "normalized": true,
3986
+ "rstrip": false,
3987
+ "single_word": false,
3988
+ "special": false
3989
+ },
3990
+ "130548": {
3991
+ "content": "<unused_token_466>",
3992
+ "lstrip": false,
3993
+ "normalized": true,
3994
+ "rstrip": false,
3995
+ "single_word": false,
3996
+ "special": false
3997
+ },
3998
+ "130549": {
3999
+ "content": "<unused_token_467>",
4000
+ "lstrip": false,
4001
+ "normalized": true,
4002
+ "rstrip": false,
4003
+ "single_word": false,
4004
+ "special": false
4005
+ },
4006
+ "130550": {
4007
+ "content": "<unused_token_468>",
4008
+ "lstrip": false,
4009
+ "normalized": true,
4010
+ "rstrip": false,
4011
+ "single_word": false,
4012
+ "special": false
4013
+ },
4014
+ "130551": {
4015
+ "content": "<unused_token_469>",
4016
+ "lstrip": false,
4017
+ "normalized": true,
4018
+ "rstrip": false,
4019
+ "single_word": false,
4020
+ "special": false
4021
+ },
4022
+ "130552": {
4023
+ "content": "<unused_token_470>",
4024
+ "lstrip": false,
4025
+ "normalized": true,
4026
+ "rstrip": false,
4027
+ "single_word": false,
4028
+ "special": false
4029
+ },
4030
+ "130553": {
4031
+ "content": "<unused_token_471>",
4032
+ "lstrip": false,
4033
+ "normalized": true,
4034
+ "rstrip": false,
4035
+ "single_word": false,
4036
+ "special": false
4037
+ },
4038
+ "130554": {
4039
+ "content": "<unused_token_472>",
4040
+ "lstrip": false,
4041
+ "normalized": true,
4042
+ "rstrip": false,
4043
+ "single_word": false,
4044
+ "special": false
4045
+ },
4046
+ "130555": {
4047
+ "content": "<unused_token_473>",
4048
+ "lstrip": false,
4049
+ "normalized": true,
4050
+ "rstrip": false,
4051
+ "single_word": false,
4052
+ "special": false
4053
+ },
4054
+ "130556": {
4055
+ "content": "<unused_token_474>",
4056
+ "lstrip": false,
4057
+ "normalized": true,
4058
+ "rstrip": false,
4059
+ "single_word": false,
4060
+ "special": false
4061
+ },
4062
+ "130557": {
4063
+ "content": "<unused_token_475>",
4064
+ "lstrip": false,
4065
+ "normalized": true,
4066
+ "rstrip": false,
4067
+ "single_word": false,
4068
+ "special": false
4069
+ },
4070
+ "130558": {
4071
+ "content": "<unused_token_476>",
4072
+ "lstrip": false,
4073
+ "normalized": true,
4074
+ "rstrip": false,
4075
+ "single_word": false,
4076
+ "special": false
4077
+ },
4078
+ "130559": {
4079
+ "content": "<unused_token_477>",
4080
+ "lstrip": false,
4081
+ "normalized": true,
4082
+ "rstrip": false,
4083
+ "single_word": false,
4084
+ "special": false
4085
+ }
4086
+ },
4087
+ "bos_token": "<s>",
4088
+ "clean_up_tokenization_spaces": false,
4089
+ "eos_token": "</s>",
4090
+ "extra_special_tokens": {},
4091
+ "legacy": true,
4092
+ "model_max_length": 1000000000000000019884624838656,
4093
+ "pad_token": "</s>",
4094
+ "sp_model_kwargs": {},
4095
+ "spaces_between_special_tokens": false,
4096
+ "tokenizer_class": "PreTrainedTokenizerFast",
4097
+ "unk_token": "<unk>",
4098
+ "use_default_system_prompt": false
4099
+ }