--- license: apache-2.0 language: - zh - en ---
MiniCPM Repo | MiniCPM Paper | MiniCPM-V Repo | Join us in Discord and WeChat
## Introduction MiniCPM3-4B is the 3rd generation of MiniCPM series. The overall performance of MiniCPM3-4B surpasses Phi-3.5-mini-Instruct and GPT-3.5-Turbo-0125, being comparable with many recent 7B~9B models. Compared to MiniCPM1.0/MiniCPM2.0, MiniCPM3-4B has a more powerful and versatile skill set to enable more general usage. MiniCPM3-4B supports function call, along with code interpreter. Please refer to [Advanced Features](https://github.com/zh-zheng/minicpm?tab=readme-ov-file#%E8%BF%9B%E9%98%B6%E5%8A%9F%E8%83%BD) for usage guidelines. MiniCPM3-4B has a 32k context window. Equipped with LLMxMapReduce, MiniCPM3-4B can handle infinite context theoretically, without requiring huge amount of memory. ## Usage ### Inference with Transformers ```python from transformers import AutoModelForCausalLM, AutoTokenizer import torch path = "openbmb/MiniCPM3-4B" device = "cuda" tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained(path, torch_dtype=torch.bfloat16, device_map=device, trust_remote_code=True) messages = [ {"role": "user", "content": "推荐5个北京的景点。"}, ] model_inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(device) model_outputs = model.generate( model_inputs, max_new_tokens=1024, top_p=0.7, temperature=0.7, repetition_penalty=1.02 ) output_token_ids = [ model_outputs[i][len(model_inputs[i]):] for i in range(len(model_inputs)) ] responses = tokenizer.batch_decode(output_token_ids, skip_special_tokens=True)[0] print(responses) ``` ### Inference with [vLLM](https://github.com/vllm-project/vllm) ```python from transformers import AutoTokenizer from vllm import LLM, SamplingParams model_name = "openbmb/MiniCPM3-4B" prompt = [{"role": "user", "content": "推荐5个北京的景点。"}] tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True) input_text = tokenizer.apply_chat_template(prompt, tokenize=False, add_generation_prompt=True) llm = LLM( model=model_name, trust_remote_code=True, tensor_parallel_size=1 ) sampling_params = SamplingParams(top_p=0.7, temperature=0.7, max_tokens=1024, repetition_penalty=1.02) outputs = llm.generate(prompts=input_text, sampling_params=sampling_params) print(outputs[0].outputs[0].text) ``` ## Evaluation ResultsBenchmark | Qwen2-7B-Instruct | GLM-4-9B-Chat | Gemma2-9B-it | Llama3.1-8B-Instruct | GPT-3.5-Turbo-0125 | Phi-3.5-mini-Instruct(3.8B) | MiniCPM3-4B | |||||||
English | ||||||||||||||
MMLU | 70.5 | 72.4 | 72.6 | 69.4 | 69.2 | 68.4 | 67.2 | |||||||
BBH | 64.9 | 76.3 | 65.2 | 67.8 | 70.3 | 68.6 | 70.2 | |||||||
MT-Bench | 8.41 | 8.35 | 7.88 | 8.28 | 8.17 | 8.60 | 8.41 | |||||||
IFEVAL (Prompt Strict-Acc.) | 51.0 | 64.5 | 71.9 | 71.5 | 58.8 | 49.4 | 68.4 | |||||||
Chinese | ||||||||||||||
CMMLU | 80.9 | 71.5 | 59.5 | 55.8 | 54.5 | 46.9 | 73.3 | |||||||
CEVAL | 77.2 | 75.6 | 56.7 | 55.2 | 52.8 | 46.1 | 73.6 | |||||||
AlignBench v1.1 | 7.10 | 6.61 | 7.10 | 5.68 | 5.82 | 5.73 | 6.74 | |||||||
FollowBench-zh (SSR) | 63.0 | 56.4 | 57.0 | 50.6 | 64.6 | 58.1 | 66.8 | |||||||
Math | ||||||||||||||
MATH | 49.6 | 50.6 | 46.0 | 51.9 | 41.8 | 46.4 | 46.6 | |||||||
GSM8K | 82.3 | 79.6 | 79.7 | 84.5 | 76.4 | 82.7 | 81.1 | |||||||
MathBench | 63.4 | 59.4 | 45.8 | 54.3 | 48.9 | 54.9 | 65.6 | |||||||
Code | ||||||||||||||
HumanEval+ | 70.1 | 67.1 | 61.6 | 62.8 | 66.5 | 68.9 | 68.3 | |||||||
MBPP+ | 57.1 | 62.2 | 64.3 | 55.3 | 71.4 | 55.8 | 63.2 | |||||||
LiveCodeBench | 22.2 | 20.2 | 19.2 | 20.4 | 24.0 | 19.6 | 22.6 | |||||||
Function Call | ||||||||||||||
BFCL | 71.6 | 70.1 | 19.2 | 73.3 | 75.4 | 48.4 | 76.0 | |||||||
Overall | ||||||||||||||
Average | 65.3 | 65.0 | 57.9 | 60.8 | 61.0 | 57.2 | 66.3 |