From 48583df175b0b10afa2225c403a34829243cb380 Mon Sep 17 00:00:00 2001 From: ymcui <16095339+ymcui@users.noreply.github.com> Date: Tue, 26 Mar 2024 15:32:04 +0800 Subject: [PATCH] update v1.2 --- README.md | 6 ++++-- README_EN.md | 6 ++++-- 2 files changed, 8 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index 4a0bedb..71004bc 100644 --- a/README.md +++ b/README.md @@ -31,7 +31,9 @@ ## 新闻 -**[2024/03/05] 开源模型训练和精调代码，发布技术报告。详情查看：[📚v1.1版本发布日志](https://github.com/ymcui/Chinese-Mixtral/releases/tag/v1.1)** +**[2024/03/26] 添加仿OpenAI API部署模式。详情查看：[📚v1.2版本发布日志](https://github.com/ymcui/Chinese-Mixtral/releases/tag/v1.2)** + +[2024/03/05] 开源模型训练和精调代码，发布技术报告。详情查看：[📚v1.1版本发布日志](https://github.com/ymcui/Chinese-Mixtral/releases/tag/v1.1) [2024/01/29] 🚀 正式发布Chinese-Mixtral（基座模型），Chinese-Mixtral-Instruct（指令/chat模型）。详情查看：[📚v1.0版本发布日志](https://github.com/ymcui/Chinese-Mixtral/releases/tag/v1.0) @@ -115,7 +117,7 @@ Mixtral是一个稀疏混合专家模型。该模型与以往的LLaMA等主流 | :----------------------------------------------------------- | ---------------------------- | :--: | :--: | :--: | :--: | :--: | :--: |:--: | | [llama.cpp](https://github.com/ggerganov/llama.cpp) | 丰富的量化选项和高效本地推理 | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | [[link]](https://github.com/ymcui/Chinese-Mixtral/wiki/llamacpp_zh) | | [🤗Transformers](https://github.com/huggingface/transformers) | 原生transformers推理接口 | ✅ | ✅ | ✅ | ✅ | ❌ | ✅ | [[link]](https://github.com/ymcui/Chinese-Mixtral/wiki/inference_with_transformers_zh) | -| [仿OpenAI API调用](https://platform.openai.com/docs/api-reference) | 仿OpenAI API接口的服务器Demo | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | [link] | +| [仿OpenAI API调用](https://platform.openai.com/docs/api-reference) | 仿OpenAI API接口的服务器Demo | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | [[link]](https://github.com/ymcui/Chinese-Mixtral/wiki/openai_api_zh) | | [text-generation-webui](https://github.com/oobabooga/text-generation-webui) | 前端Web UI界面的部署方式 | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | [[link]](https://github.com/ymcui/Chinese-Mixtral/wiki/text-generation-webui_zh) | | [LangChain](https://github.com/hwchase17/langchain) | 适合二次开发的大模型应用开源框架 | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | [link] | | [privateGPT](https://github.com/imartinez/privateGPT) | 多文档本地问答框架 | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | [link] | diff --git a/README_EN.md b/README_EN.md index 96b857f..fce3708 100644 --- a/README_EN.md +++ b/README_EN.md @@ -31,7 +31,9 @@ This project is developed based on the [Mixtral model](https://huggingface.co/mi ## News -**[2024/03/05] Release pre-training and fine-tuning scripts. Technical reports are also available. See: [📚 v1.1 Release Notes](https://github.com/ymcui/Chinese-Mixtral/releases/tag/v1.1)** +**[2024/03/26] Add deployment method of OpenAI-style API. See: [📚v1.2 Release Notes](https://github.com/ymcui/Chinese-Mixtral/releases/tag/v1.2)** + +[2024/03/05] Release pre-training and fine-tuning scripts. Technical reports are also available. See: [📚 v1.1 Release Notes](https://github.com/ymcui/Chinese-Mixtral/releases/tag/v1.1) [2024/01/29] 🚀 Official release of Chinese-Mixtral (Base Model), Chinese-Mixtral-Instruct (Instruction/Chat Model). For more details, see: [📚 v1.0 Release Notes](https://github.com/ymcui/Chinese-Mixtral/releases/tag/v1.0) @@ -115,7 +117,7 @@ The related models in this project mainly support the following quantization, in | ------------------------------------------------------------ | ------------------------------------------------------------ | :--: | :--: | :----------: | :--: | :--: | :--: | :----------------------------------------------------------: | | [llama.cpp](https://github.com/ggerganov/llama.cpp) | Rich quantization options and efficient local inference | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | [[link]](https://github.com/ymcui/Chinese-Mixtral/wiki/llamacpp_en) | | [🤗Transformers](https://github.com/huggingface/transformers) | Native transformers inference interface | ✅ | ✅ | ✅ | ✅ | ❌ | ✅ | [[link]](https://github.com/ymcui/Chinese-Mixtral/wiki/inference_with_transformers_en) | -| [Imitation OpenAI API Call](https://platform.openai.com/docs/api-reference) | Server Demo with OpenAI API-like interface | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | [link] | +| [Imitation OpenAI API Call](https://platform.openai.com/docs/api-reference) | Server Demo with OpenAI API-like interface | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | [[link]](https://github.com/ymcui/Chinese-Mixtral/wiki/openai_api_en) | | [text-generation-webui](https://github.com/oobabooga/text-generation-webui) | Frontend Web UI deployment method | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | [[link]](https://github.com/ymcui/Chinese-Mixtral/wiki/text-generation-webui_en) | | [LangChain](https://github.com/hwchase17/langchain) | Open-source framework for large model applications suitable for secondary development | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | [link] | | [privateGPT](https://github.com/imartinez/privateGPT) | Local multi-document Q&A framework | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | [link] |