104 lines
3.5 KiB
Markdown
104 lines
3.5 KiB
Markdown
---
|
||
library_name: transformers
|
||
license: apache-2.0
|
||
language:
|
||
- en
|
||
- zh
|
||
base_model: openbmb/MiniCPM5-1B
|
||
base_model_relation: finetune
|
||
pipeline_tag: text-generation
|
||
tags:
|
||
- minicpm
|
||
- minicpm5
|
||
- thinking
|
||
- fable5
|
||
- coding
|
||
- instruction-following
|
||
---
|
||
|
||
<p align="center">
|
||
<img src="assets/banner.png" alt="MiniCPM5-1B-Claude-Opus-Fable5-Thinking" width="100%"/>
|
||
</p>
|
||
|
||
# MiniCPM5-1B-Claude-Opus-Fable5-Thinking
|
||
|
||
GGUF 量化版：**[MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF](https://huggingface.co/GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF)**
|
||
|
||
[English README](./README.md)
|
||
|
||
**MiniCPM5-1B-Claude-Opus-Fable5-Thinking** 是基于 [openbmb/MiniCPM5-1B](https://huggingface.co/openbmb/MiniCPM5-1B) 的 1B **Thinking** 语言模型。该模型使用 **Fable 5** 数据进一步微调，增强了 **Coding（编程）** 与 **指令遵循（Instruction Following）** 能力，同时保留 MiniCPM5 原生的 Thinking 对话模板与工具调用格式。
|
||
|
||
llama.cpp / Ollama / LM Studio 部署请参阅 **[GGUF 仓库](https://huggingface.co/GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF)**。
|
||
|
||
---
|
||
|
||
## 模型概述
|
||
|
||
| 项目 | 说明 |
|
||
|---|---|
|
||
| **基座模型** | [openbmb/MiniCPM5-1B](https://huggingface.co/openbmb/MiniCPM5-1B)（1B 稠密 Llama 架构） |
|
||
| **后训练数据** | Fable 5 traces |
|
||
| **主要提升** | 相较基座，Coding 与指令遵循能力更强 |
|
||
| **对话格式** | MiniCPM5 原生 Thinking 模板，支持可选的思维链推理块 |
|
||
| **上下文长度** | **128K**（`max_position_embeddings = 131072`） |
|
||
| **部署特点** | 单卡友好，适合边缘 / 本地场景 |
|
||
|
||
---
|
||
|
||
## 能力
|
||
|
||
- **Coding** — 代码生成、调试及软件工程类任务
|
||
- **Instruction Following** — 更稳定地遵循用户提示与结构化任务约束
|
||
- **Thinking 模式** — 通过 MiniCPM5 对话模板进行思维链推理
|
||
- **工具调用** — 继承 MiniCPM5 的 XML 工具调用格式
|
||
- **长上下文** — 最高 **128K tokens**（`config.json` 中为 131,072）
|
||
|
||
---
|
||
|
||
## 快速开始
|
||
|
||
```python
|
||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||
import torch
|
||
|
||
model_id = "GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking"
|
||
|
||
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
|
||
model = AutoModelForCausalLM.from_pretrained(
|
||
model_id, trust_remote_code=True,
|
||
torch_dtype=torch.bfloat16, device_map="auto",
|
||
)
|
||
|
||
messages = [{"role": "user", "content": "写一个 Python 函数，合并两个有序链表。"}]
|
||
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||
inputs = tokenizer(text, return_tensors="pt").to(model.device)
|
||
outputs = model.generate(**inputs, max_new_tokens=512, do_sample=False)
|
||
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
|
||
```
|
||
|
||
---
|
||
|
||
## 采样建议
|
||
|
||
生成参数继承自 **[MiniCPM5-1B](https://huggingface.co/openbmb/MiniCPM5-1B)**：
|
||
|
||
| 模式 | 参数 |
|
||
|---|---|
|
||
| **Think**（默认） | `temperature=0.9, top_p=0.95` |
|
||
| **No Think** | `temperature=0.7, top_p=0.95`，`enable_thinking=False` |
|
||
|
||
---
|
||
|
||
## 局限性
|
||
|
||
- **Thinking 输出** — 模型可能在最终回答前输出推理块；下游应用可在展示前将其剥离
|
||
- **1B 体量** — 面向轻量本地部署，非前沿规模通用推理模型
|
||
|
||
---
|
||
|
||
## 许可与致谢
|
||
|
||
- 许可证：**Apache-2.0**（继承自 MiniCPM5-1B）
|
||
- 基座：[OpenBMB / MiniCPM5-1B](https://huggingface.co/openbmb/MiniCPM5-1B)
|
||
- GGUF：[llama.cpp](https://github.com/ggml-org/llama.cpp)
|