CoolFace
Modelpublic

openbmb/BitCPM4-1B-GGUF

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face
6likes90downloads
Model Card

<div align="center"> <img src="https://github.com/OpenBMB/MiniCPM/blob/main/assets/minicpm_logo.png?raw=true" width="500em" ></img> </div>

<p align="center"> <a href="https://github.com/OpenBMB/MiniCPM/" target="blank">GitHub Repo</a> | <a href="https://github.com/OpenBMB/MiniCPM/tree/main/report/MiniCPM4TechnicalReport.pdf" target="blank">Technical Report</a> </p> <p align="center"> πŸ‘‹ Join us on <a href="https://discord.gg/3cGQn9b3YM" target="blank">Discord</a> and <a href="https://github.com/OpenBMB/MiniCPM/blob/main/assets/wechat.jpg" target="_blank">WeChat</a> </p>

What's New

  • β€”[2025.06.06] MiniCPM4 series are released! This model achieves ultimate efficiency improvements while maintaining optimal performance at the same scale! It can achieve over 5x generation acceleration on typical end-side chips! You can find technical report here.πŸ”₯πŸ”₯πŸ”₯

MiniCPM4 Series

MiniCPM4 series are highly efficient large language models (LLMs) designed explicitly for end-side devices, which achieves this efficiency through systematic innovation in four key dimensions: model architecture, training data, training algorithms, and inference systems.

  • β€”MiniCPM4-8B: The flagship of MiniCPM4, with 8B parameters, trained on 8T tokens.
  • β€”MiniCPM4-0.5B: The small version of MiniCPM4, with 0.5B parameters, trained on 1T tokens.
  • β€”MiniCPM4-8B-Eagle-FRSpec: Eagle head for FRSpec, accelerating speculative inference for MiniCPM4-8B.
  • β€”MiniCPM4-8B-Eagle-FRSpec-QAT-cpmcu: Eagle head trained with QAT for FRSpec, efficiently integrate speculation and quantization to achieve ultra acceleration for MiniCPM4-8B.
  • β€”MiniCPM4-8B-Eagle-vLLM: Eagle head in vLLM format, accelerating speculative inference for MiniCPM4-8B.
  • β€”MiniCPM4-8B-marlin-Eagle-vLLM: Quantized Eagle head for vLLM format, accelerating speculative inference for MiniCPM4-8B.
  • β€”BitCPM4-0.5B: Extreme ternary quantization applied to MiniCPM4-0.5B compresses model parameters into ternary values, achieving a 90% reduction in bit width.
  • β€”BitCPM4-1B: Extreme ternary quantization applied to MiniCPM3-1B compresses model parameters into ternary values, achieving a 90% reduction in bit width.
  • β€”MiniCPM4-Survey: Based on MiniCPM4-8B, accepts users' quiries as input and autonomously generate trustworthy, long-form survey papers.
  • β€”MiniCPM4-MCP: Based on MiniCPM4-8B, accepts users' queries and available MCP tools as input and autonomously calls relevant MCP tools to satisfy users' requirements.
  • β€”BitCPM4-0.5B-GGUF: GGUF version of BitCPM4-0.5B.
  • β€”BitCPM4-1B-GGUF: GGUF version of BitCPM4-1B. (<-- you are here)

Introduction

BitCPM4 are ternary quantized models derived from the MiniCPM series models through quantization-aware training (QAT), achieving significant improvements in both training efficiency and model parameter efficiency.

  • β€”Improvements of the training method
  • β€”Searching hyperparameters with a wind-tunnel on a small model.
  • β€”Using a two-stage training method: training in high-precision first and then QAT, making the best of the trained high-precision models and significantly reducing the computational resources required for the QAT phase.
  • β€”High parameter efficiency
  • β€”Achieving comparable performance to full-precision models of similar parameter models with a bit width of only 1.58 bits, demonstrating high parameter efficiency.

Usage

Inference with llama.cpp

bash
./llama-cli -c 1024 -m BitCPM4-1B-q4_0.gguf -n 1024 --top-p 0.7 --temp 0.7 --prompt "θ―·ε†™δΈ€η―‡ε…³δΊŽδΊΊε·₯ζ™Ίθƒ½ηš„ζ–‡η« οΌŒθ―¦η»†δ»‹η»δΊΊε·₯ζ™Ίθƒ½ηš„ζœͺζ₯ε‘ε±•ε’Œιšζ‚£γ€‚"

Evaluation Results

BitCPM4's performance is comparable with other full-precision models in same model size. Benchmark of BitCPM

Statement

  • β€”As a language model, MiniCPM generates content by learning from a vast amount of text.
  • β€”However, it does not possess the ability to comprehend or express personal opinions or value judgments.
  • β€”Any content generated by MiniCPM does not represent the viewpoints or positions of the model developers.
  • β€”Therefore, when using content generated by MiniCPM, users should take full responsibility for evaluating and verifying it on their own.

LICENSE

  • β€”This repository and MiniCPM models are released under the Apache-2.0 License.

Citation

  • β€”Please cite our paper if you find our work valuable.
bibtex
@article{minicpm4,
  title={{MiniCPM4}: Ultra-Efficient LLMs on End Devices},
  author={MiniCPM Team},
  year={2025}
}