diff --git a/README.md b/README.md index 9c5da5b..78bd4f4 100644 --- a/README.md +++ b/README.md @@ -79,16 +79,24 @@ 希望此开源项目可以帮助LLM初学者快速入门! -👉**最近更新** +👉**Recent Updates**
- 2024-09-01 (new🎉) - - 更新MiniMind-V1 (108M)模型,采用minimind_tokenizer,预训练轮次3 + SFT轮次10,更充分训练,性能更强。 + September 1, 2024 (new🎉) + +- Updated MiniMind-V1 (108M) model, using minimind_tokenizer, with 3 rounds of pre-training + 10 rounds of SFT, more thorough training, stronger performance. + +- The project has been deployed to the ModelScope Creation Space, where you can experience it on this website: + +- [ModelScope Online Experience](https://www.modelscope.cn/studios/gongjy/minimind) +
- 2024-08-27 - - 项目首次开源 + August 27, 2024 + +- Project first open-sourced +
# 📌 Environment @@ -101,24 +109,44 @@ * CUDA == 12.2 * [requirements.txt](./requirements.txt) -# 📌 Start Inference +# 📌 Deployment & Inference
Hugging Face Logo Hugging Face -[MiniMind-Collection](https://huggingface.co/collections/jingyaogong/minimind-66caf8d999f5c7fa64f399e5) +[MiniMind (HuggingFace)](https://huggingface.co/collections/jingyaogong/minimind-66caf8d999f5c7fa64f399e5) + + Hugging Face Logo + +[MiniMind (ModelScope)](https://www.modelscope.cn/models/gongjy/MiniMind-V1) +
```bash # step 1 -git clone https://huggingface.co/jingyaogong/minimind +git clone https://huggingface.co/jingyaogong/minimind-v1 ``` ```bash # step 2 python 2-eval.py ``` +或者启动streamlit,启动网页聊天界面 +```bash +# or step 3, use streamlit +streamlit run fast_inference.py +``` +![](./images/streamlit.png) + +
+ +项目已部署至ModelScope创空间,可以在此网站上体验: + +[ModelScope在线体验](https://www.modelscope.cn/studios/gongjy/minimind) + + +
# 📌 Quick Start diff --git a/README_en.md b/README_en.md index 856f8d6..7c41592 100644 --- a/README_en.md +++ b/README_en.md @@ -101,18 +101,23 @@ These are my personal software and hardware environment configurations. Please a * CUDA == 12.2 * [requirements.txt](./requirements.txt) -# 📌 Start Inference +# 📌 Deployment & Inference
Hugging Face Logo Hugging Face -[MiniMind-Collection](https://huggingface.co/collections/jingyaogong/minimind-66caf8d999f5c7fa64f399e5) +[MiniMind (HuggingFace)](https://huggingface.co/collections/jingyaogong/minimind-66caf8d999f5c7fa64f399e5) + + Hugging Face Logo + +[MiniMind (ModelScope)](https://www.modelscope.cn/models/gongjy/MiniMind-V1) +
```bash # step 1 -git clone https://huggingface.co/jingyaogong/minimind +git clone https://huggingface.co/jingyaogong/minimind-v1 ``` ```bash @@ -120,6 +125,22 @@ git clone https://huggingface.co/jingyaogong/minimind python 2-eval.py ``` +or you can run streamlit, launch a web page to chat with minimind-v1 +```bash +# or step 3, use streamlit +streamlit run fast_inference.py +``` +![](./images/streamlit.png) + + +
+ +The project has been deployed to ModelScope makerspace, where you can experience: + +[ModelScope Online](https://www.modelscope.cn/studios/gongjy/minimind) + + +
# 📌 Quick Start *