Instructions to use nvcky/MiniFABLECPM5-Thinking with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvcky/MiniFABLECPM5-Thinking with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="nvcky/MiniFABLECPM5-Thinking")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nvcky/MiniFABLECPM5-Thinking")
model = AutoModelForCausalLM.from_pretrained("nvcky/MiniFABLECPM5-Thinking")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nvcky/MiniFABLECPM5-Thinking with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvcky/MiniFABLECPM5-Thinking"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvcky/MiniFABLECPM5-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvcky/MiniFABLECPM5-Thinking

SGLang

How to use nvcky/MiniFABLECPM5-Thinking with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "nvcky/MiniFABLECPM5-Thinking" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvcky/MiniFABLECPM5-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "nvcky/MiniFABLECPM5-Thinking" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvcky/MiniFABLECPM5-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvcky/MiniFABLECPM5-Thinking with Docker Model Runner:
```
docker model run hf.co/nvcky/MiniFABLECPM5-Thinking
```

MiniFABLECPM5-Thinking / README-cn.md

nvcky

Duplicate from GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking

7a7e80a 1 day ago

preview code

Raw

History Blame Contribute Delete

3.95 kB

	---
	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

	> 📢 V2.0 已发布 — 我们已发布增强工具调用能力的新版本，欢迎通过以下链接下载体验：
	> - Transformers：[MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking](https://huggingface.co/GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking)
	> - GGUF：[MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-GGUF](https://huggingface.co/GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-GGUF)

	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)