RYDE-WORK/MiniCPM
1
0
Fork 0
mirror of https://github.com/RYDE-WORK/MiniCPM.git synced 2026-01-19 21:03:39 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Update README-en.md

Browse Source
This commit is contained in:
DingDing 2024-02-02 17:05:19 +08:00 committed by GitHub
parent f8aaf7c6ad
commit 1994166f0a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README-en.md
View File

@ -22,7 +22,7 @@ MiniCPM is an End-Side LLM developed by ModelBest Inc. and TsinghuaNLP, with onl
- MiniCPM has very close performance compared with Mistral-7B on open-sourced general benchmarks with better ability on Chinese, Mathmetics and Coding after SFT. The overall performance exceeds Llama2-13B, MPT-30B, Falcon-40B, etc.
- After DPO, MiniCPM outperforms Llama2-70B-Chat, Vicuna-33B, Mistral-7B-Instruct-v0.1, Zephyr-7B-alpha, etc. on MTBench.
- MiniCPM-V, based on MiniCPM-2B, achieves the best overall performance among multimodel models of the same scale, surpassing existing multimodal large models built on Phi-2 and achieving performance comparable to or even better than 9.6B Qwen-VL-Chat on some tasks.
- MiniCPM can be deployed and infer on smartphones, and the speed of streaming output is relatively higher than human verbal speed. MiniCPM-V is the first multi-modal models that can be deployed on smartphones.
- MiniCPM can be deployed and infer on smartphones, and the speed of streaming output is relatively higher than human verbal speed. MiniCPM-V has also successfully deployed multi-modal models on smartphones.
- The cost of developing based on MiniCPM is low. Parameter efficient finetuning can be conducted with a single 1080/2080 GPU and full parameter finetuning can be conducted with a 3090/4090 GPU.
We release all model parameters for research and limited commercial use. In future, we will also release all the checkpoint during training and most public training data for research on model mechanism.