From b192a8032c92fefebc6ef984fd8cf789f4637f2a Mon Sep 17 00:00:00 2001 From: Jason Dai Date: Mon, 16 Oct 2023 10:54:52 +0800 Subject: [PATCH] Update llm-readme (#9176) --- README.md | 2 +- python/llm/README.md | 49 ++++++++++++++++++++++---------------------- 2 files changed, 25 insertions(+), 26 deletions(-) diff --git a/README.md b/README.md index 3b637337..6089f7dc 100644 --- a/README.md +++ b/README.md @@ -15,7 +15,7 @@ - **[New]** `bigdl-llm` now supports QLoRA fintuning on Intel GPU; see the the example [here](python/llm/example/GPU/QLoRA-FineTuning). - `bigdl-llm` now supports Intel GPU (including Arc, Flex and MAX); see the the latest GPU examples [here](python/llm/example/GPU). - `bigdl-llm` tutorial is released [here](https://github.com/intel-analytics/bigdl-llm-tutorial). -- Over 20 models have been optimized/verified on `bigdl-llm`, including *LLaMA/LLaMA2, ChatGLM/ChatGLM2, MPT, Falcon, Dolly, StarCoder, Whisper, InternLM, QWen, Baichuan, Aquila, MOSS,* and more; see the complete list [here](python/llm/README.md#verified-models). +- Over 20 models have been optimized/verified on `bigdl-llm`, including *LLaMA/LLaMA2, ChatGLM/ChatGLM2, Mistral, Falcon, MPT, Dolly, StarCoder, Whisper, Baichuan, InternLM, QWen, Aquila, MOSS,* and more; see the complete list [here](python/llm/README.md#verified-models). ### `bigdl-llm` Demos See the ***optimized performance*** of `chatglm2-6b` and `llama-2-13b-chat` models on 12th Gen Intel Core CPU and Intel Arc GPU below. diff --git a/python/llm/README.md b/python/llm/README.md index 63cd54fa..c7364086 100644 --- a/python/llm/README.md +++ b/python/llm/README.md @@ -34,32 +34,31 @@ See the ***optimized performance*** of `chatglm2-6b` and `llama-2-13b-chat` mode ### Verified models -Over 20 models have been optimized/verified on `bigdl-llm`, including *LLaMA/LLaMA2, ChatGLM/ChatGLM2, MPT, Falcon, Dolly-v1/Dolly-v2, StarCoder, Whisper, InternLM, QWen, Baichuan, MOSS,* and more; see the complete list below. +Over 20 models have been optimized/verified on `bigdl-llm`, including *LLaMA/LLaMA2, ChatGLM/ChatGLM2, Mistral, Falcon, MPT, Dolly, StarCoder, Whisper, Baichuan, InternLM, QWen, Aquila, MOSS,* and more; see the complete list below. + +| Model | CPU Example | GPU Example | +|------------|----------------------------------------------------------------|-----------------------------------------------------------------| +| LLaMA *(such as Vicuna, Guanaco, Koala, Baize, WizardLM, etc.)* | [link1](example/CPU/Native-Models), [link2](example/CPU/HF-Transformers-AutoModels/Model/vicuna) |[link](example/GPU/HF-Transformers-AutoModels/Model/vicuna)| +| LLaMA 2 | [link1](example/CPU/Native-Models), [link2](example/CPU/HF-Transformers-AutoModels/Model/llama2) | [link](example/GPU/HF-Transformers-AutoModels/Model/llama2) | +| ChatGLM | [link](example/CPU/HF-Transformers-AutoModels/Model/chatglm) | | +| ChatGLM2 | [link](example/CPU/HF-Transformers-AutoModels/Model/chatglm2) | [link](example/GPU/HF-Transformers-AutoModels/Model/chatglm2) | +| Mistral | [link](example/CPU/HF-Transformers-AutoModels/Model/mistral) | [link](example/GPU/HF-Transformers-AutoModels/Model/mistral) | +| Falcon | [link](example/CPU/HF-Transformers-AutoModels/Model/falcon) | [link](example/GPU/HF-Transformers-AutoModels/Model/falcon) | +| MPT | [link](example/CPU/HF-Transformers-AutoModels/Model/mpt) | [link](example/CPU/HF-Transformers-AutoModels/Model/mpt) | +| Dolly-v1 | [link](example/CPU/HF-Transformers-AutoModels/Model/dolly_v1) | [link](example/CPU/HF-Transformers-AutoModels/Model/dolly_v1) | +| Dolly-v2 | [link](example/CPU/HF-Transformers-AutoModels/Model/dolly_v2) | [link](example/CPU/HF-Transformers-AutoModels/Model/dolly_v2) | +| Replit Code| [link](example/CPU/HF-Transformers-AutoModels/Model/replit) | [link](example/CPU/HF-Transformers-AutoModels/Model/replit) | +| RedPajama | [link1](example/CPU/Native-Models), [link2](example/CPU/HF-Transformers-AutoModels/Model/redpajama) | | +| Phoenix | [link1](example/CPU/Native-Models), [link2](example/CPU/HF-Transformers-AutoModels/Model/phoenix) | | +| StarCoder | [link1](example/CPU/Native-Models), [link2](example/CPU/HF-Transformers-AutoModels/Model/starcoder) | [link](example/GPU/HF-Transformers-AutoModels/Model/starcoder) | +| Baichuan | [link](example/CPU/HF-Transformers-AutoModels/Model/baichuan) | [link](example/CPU/HF-Transformers-AutoModels/Model/baichuan) | +| Baichuan2 | [link](example/CPU/HF-Transformers-AutoModels/Model/baichuan2) | [link](example/GPU/HF-Transformers-AutoModels/Model/baichuan2) | +| InternLM | [link](example/CPU/HF-Transformers-AutoModels/Model/internlm) | [link](example/GPU/HF-Transformers-AutoModels/Model/internlm) | +| Qwen | [link](example/CPU/HF-Transformers-AutoModels/Model/qwen) | [link](example/GPU/HF-Transformers-AutoModels/Model/qwen) | +| Aquila | [link](example/CPU/HF-Transformers-AutoModels/Model/aquila) | [link](example/GPU/HF-Transformers-AutoModels/Model/aquila) | +| MOSS | [link](example/CPU/HF-Transformers-AutoModels/Model/moss) | | +| Whisper | [link](example/CPU/HF-Transformers-AutoModels/Model/whisper) | [link](example/GPU/HF-Transformers-AutoModels/Model/whisper) | -
Table of verified models - -| Model | Example | -|-----------|----------------------------------------------------------| -| LLaMA *(such as Vicuna, Guanaco, Koala, Baize, WizardLM, etc.)* | [link1](example/CPU/Native-Models), [link2](example/CPU/HF-Transformers-AutoModels/Model/vicuna) | -| LLaMA 2 | [link](example/CPU/HF-Transformers-AutoModels/Model/llama2) | -| MPT | [link](example/CPU/HF-Transformers-AutoModels/Model/mpt) | -| Falcon | [link](example/CPU/HF-Transformers-AutoModels/Model/falcon) | -| ChatGLM | [link](example/CPU/HF-Transformers-AutoModels/Model/chatglm) | -| ChatGLM2 | [link](example/CPU/HF-Transformers-AutoModels/Model/chatglm2) | -| Qwen | [link](example/CPU/HF-Transformers-AutoModels/Model/qwen) | -| MOSS | [link](example/CPU/HF-Transformers-AutoModels/Model/moss) | -| Baichuan | [link](example/CPU/HF-Transformers-AutoModels/Model/baichuan) | -| Baichuan2 | [link](example/CPU/HF-Transformers-AutoModels/Model/baichuan2) | -| Dolly-v1 | [link](example/CPU/HF-Transformers-AutoModels/Model/dolly_v1) | -| Dolly-v2 | [link](example/CPU/HF-Transformers-AutoModels/Model/dolly_v2) | -| RedPajama | [link1](example/CPU/Native-Models), [link2](example/CPU/HF-Transformers-AutoModels/Model/redpajama) | -| Phoenix | [link1](example/CPU/Native-Models), [link2](example/CPU/HF-Transformers-AutoModels/Model/phoenix) | -| StarCoder | [link1](example/CPU/Native-Models), [link2](example/CPU/HF-Transformers-AutoModels/Model/starcoder) | -| InternLM | [link](example/CPU/HF-Transformers-AutoModels/Model/internlm) | -| Whisper | [link](example/CPU/HF-Transformers-AutoModels/Model/whisper) | -| Aquila | [link](example/CPU/HF-Transformers-AutoModels/Model/aquila) | - -
### Working with `bigdl-llm`