Instructions to use openbmb/MiniCPM5-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openbmb/MiniCPM5-1B with Transformers:

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

pipe = pipeline("text-generation", model="openbmb/MiniCPM5-1B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openbmb/MiniCPM5-1B")
model = AutoModelForCausalLM.from_pretrained("openbmb/MiniCPM5-1B")
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

vLLM

How to use openbmb/MiniCPM5-1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openbmb/MiniCPM5-1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openbmb/MiniCPM5-1B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/openbmb/MiniCPM5-1B

SGLang

How to use openbmb/MiniCPM5-1B 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 "openbmb/MiniCPM5-1B" \
    --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": "openbmb/MiniCPM5-1B",
		"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 "openbmb/MiniCPM5-1B" \
        --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": "openbmb/MiniCPM5-1B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openbmb/MiniCPM5-1B with Docker Model Runner:
```
docker model run hf.co/openbmb/MiniCPM5-1B
```

BigDong commited on 2 days ago

Commit

b282ae7

1 Parent(s): ab959d9

minor update

Browse files

Files changed (2) hide show

README-cn.md +1 -1
README.md +1 -1

README-cn.md CHANGED Viewed

@@ -98,7 +98,7 @@ MiniCPM5-1B 的训练过程是 **[UltraData 分级数据管理体系](https://ar
 **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。
-**RL** 阶段组合了多类互补训练信号。Reasoning RL 使用 [DAPO-Math-17k](https://huggingface.co/datasets/BytedTsinghua-SIA/DAPO-Math-17k) 强化数学推理；闭卷问答使用 [TriviaQA](https://huggingface.co/datasets/mandarjoshi/trivia_qa) 和 [NQ-Open](https://huggingface.co/datasets/google-research-datasets/nq_open)，并通过系统提示引导模型在不确定时承认不知道，而不是随机猜测。写作能力来自 [LongWriter-Zero-RLData](https://huggingface.co/datasets/THU-KEG/LongWriter-Zero-RLData)；指令跟随和长上下文理解则使用从通用语料合成的可验证 RLVR 数据。通用对话部分基于 anchor responses 构造 pair-wise RLHF 信号，由 Generative Reward Model 进行偏好判断。
 ![MiniCPM5-1B RL 两阶段流程](https://raw.githubusercontent.com/OpenBMB/MiniCPM/minicpm5/assets/minicpm5/rl_two_stage_overview.png)

 **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。
+**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) 采用两阶段长度调度，逐步降低超长率并提升推理准确率。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。
 ![MiniCPM5-1B RL 两阶段流程](https://raw.githubusercontent.com/OpenBMB/MiniCPM/minicpm5/assets/minicpm5/rl_two_stage_overview.png)

README.md CHANGED Viewed

@@ -98,7 +98,7 @@ During **post-training**, we proceed in three steps: **SFT**, **RL**, and **OPD*
 **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.
-**RL** combines several complementary training signals. Reasoning RL uses [DAPO-Math-17k](https://huggingface.co/datasets/BytedTsinghua-SIA/DAPO-Math-17k) to strengthen mathematical reasoning. Closed-book QA uses [TriviaQA](https://huggingface.co/datasets/mandarjoshi/trivia_qa) and [NQ-Open](https://huggingface.co/datasets/google-research-datasets/nq_open), with a system prompt that encourages the model to acknowledge uncertainty instead of guessing. Writing is trained with [LongWriter-Zero-RLData](https://huggingface.co/datasets/THU-KEG/LongWriter-Zero-RLData); instruction following and long-context comprehension use verifiable RLVR data synthesized from general corpora. For general dialogue, we build pair-wise RLHF signals from anchor responses and use a Generative Reward Model for preference judgment.
 ![MiniCPM5-1B RL Two-stage Pipeline](https://raw.githubusercontent.com/OpenBMB/MiniCPM/minicpm5/assets/minicpm5/rl_two_stage_overview.png)

 **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.
+**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) 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.
 ![MiniCPM5-1B RL Two-stage Pipeline](https://raw.githubusercontent.com/OpenBMB/MiniCPM/minicpm5/assets/minicpm5/rl_two_stage_overview.png)