From 3ee194d9830bfc0b19b5334e2fbbc597f9f5b0f8 Mon Sep 17 00:00:00 2001 From: Jinhe Date: Tue, 20 Aug 2024 18:01:42 +0800 Subject: [PATCH] Pytorch models transformers version update (#11860) * yi sync * delete 4.34 constraint * delete 4.34 constraint * delete 4.31 constraint * delete 4.34 constraint * delete 4.35 constraint * added <=4.33.3 constraint * added <=4.33.3 constraint * switched to chinese prompt --- .../llm/example/GPU/HuggingFace/LLM/yi/README.md | 12 ++++++------ .../llm/example/GPU/HuggingFace/LLM/yi/generate.py | 2 +- .../GPU/PyTorch-Models/Model/codegeex2/README.md | 2 -- .../GPU/PyTorch-Models/Model/codellama/README.md | 4 ---- .../GPU/PyTorch-Models/Model/deciLM-7b/README.md | 2 -- .../GPU/PyTorch-Models/Model/mistral/README.md | 7 ------- .../GPU/PyTorch-Models/Model/replit/README.md | 4 +++- .../GPU/PyTorch-Models/Model/solar/README.md | 4 ---- .../example/GPU/PyTorch-Models/Model/yi/README.md | 14 ++++++++++++-- .../GPU/PyTorch-Models/Model/yi/generate.py | 2 +- 10 files changed, 23 insertions(+), 30 deletions(-) diff --git a/python/llm/example/GPU/HuggingFace/LLM/yi/README.md b/python/llm/example/GPU/HuggingFace/LLM/yi/README.md index 1fb49f21..080e2676 100644 --- a/python/llm/example/GPU/HuggingFace/LLM/yi/README.md +++ b/python/llm/example/GPU/HuggingFace/LLM/yi/README.md @@ -122,18 +122,18 @@ In the example, several arguments can be passed to satisfy your requirements: ```log Inference time: xxxx s -------------------- Prompt -------------------- -What is AI? +AI是什么？ -------------------- Output -------------------- -What is AI? -Artificial Intelligence (AI) is the simulation of human intelligence in machines. AI is the science and engineering of making intelligent machines, especially intelligent computer programs. +AI是什么？ +人工智能（Artificial Intelligence），英文缩写为AI。它是研究、开发用于模拟、延伸和扩展人的智能的理论、方法、技术及 ``` #### [01-ai/Yi-6B-Chat](https://huggingface.co/01-ai/Yi-6B-Chat) ```log Inference time: xxxx s -------------------- Prompt -------------------- -What is AI? +AI是什么？ -------------------- Output -------------------- -What is AI? -Artificial Intelligence (AI) refers to the simulation of human intelligence processes by machines, especially computer systems. These processes include learning, reasoning, and self- +AI是什么？ +人工智能（Artificial Intelligence, AI）是计算机科学的一个分支，它研究如何让计算机模拟人类的智能行为。人工智能可以通过模仿人类的思维过程和 ``` \ No newline at end of file diff --git a/python/llm/example/GPU/HuggingFace/LLM/yi/generate.py b/python/llm/example/GPU/HuggingFace/LLM/yi/generate.py index f32f272c..643c5f7b 100644 --- a/python/llm/example/GPU/HuggingFace/LLM/yi/generate.py +++ b/python/llm/example/GPU/HuggingFace/LLM/yi/generate.py @@ -27,7 +27,7 @@ if __name__ == '__main__': parser.add_argument('--repo-id-or-model-path', type=str, default="01-ai/Yi-6B-Chat", help='The huggingface repo id for the Yi model to be downloaded' ', or the path to the huggingface checkpoint folder') - parser.add_argument('--prompt', type=str, default="What is AI?", + parser.add_argument('--prompt', type=str, default="AI是什么？", help='Prompt to infer') parser.add_argument('--n-predict', type=int, default=32, help='Max tokens to predict') diff --git a/python/llm/example/GPU/PyTorch-Models/Model/codegeex2/README.md b/python/llm/example/GPU/PyTorch-Models/Model/codegeex2/README.md index 37f801a2..bc8cfa62 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/codegeex2/README.md +++ b/python/llm/example/GPU/PyTorch-Models/Model/codegeex2/README.md @@ -16,7 +16,6 @@ conda create -n llm python=3.11 conda activate llm # below command will install intel_extension_for_pytorch==2.1.10+xpu as default pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/ -pip install transformers==4.31.0 ``` #### 1.2 Installation on Windows @@ -27,7 +26,6 @@ conda activate llm # below command will install intel_extension_for_pytorch==2.1.10+xpu as default pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/ -pip install transformers==4.31.0 ``` ### 2. Configures OneAPI environment variables for Linux diff --git a/python/llm/example/GPU/PyTorch-Models/Model/codellama/README.md b/python/llm/example/GPU/PyTorch-Models/Model/codellama/README.md index 497a6828..ff68817e 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/codellama/README.md +++ b/python/llm/example/GPU/PyTorch-Models/Model/codellama/README.md @@ -14,8 +14,6 @@ conda create -n llm python=3.11 conda activate llm # below command will install intel_extension_for_pytorch==2.1.10+xpu as default pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/ - -pip install transformers==4.34.1 # CodeLlamaTokenizer is supported in higher version of transformers ``` #### 1.2 Installation on Windows @@ -26,8 +24,6 @@ conda activate llm # below command will install intel_extension_for_pytorch==2.1.10+xpu as default pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/ - -pip install transformers==4.34.1 # CodeLlamaTokenizer is supported in higher version of transformers ``` ### 2. Configures OneAPI environment variables for Linux diff --git a/python/llm/example/GPU/PyTorch-Models/Model/deciLM-7b/README.md b/python/llm/example/GPU/PyTorch-Models/Model/deciLM-7b/README.md index ff8eab5a..a9e66f54 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/deciLM-7b/README.md +++ b/python/llm/example/GPU/PyTorch-Models/Model/deciLM-7b/README.md @@ -14,8 +14,6 @@ conda create -n llm python=3.11 conda activate llm # below command will install intel_extension_for_pytorch==2.1.10+xpu as default pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/ - -pip install transformers==4.35.2 # required by DeciLM-7B ``` #### 1.2 Installation on Windows diff --git a/python/llm/example/GPU/PyTorch-Models/Model/mistral/README.md b/python/llm/example/GPU/PyTorch-Models/Model/mistral/README.md index 4fc017e1..4f3e58b0 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/mistral/README.md +++ b/python/llm/example/GPU/PyTorch-Models/Model/mistral/README.md @@ -4,7 +4,6 @@ In this directory, you will find examples on how you could use IPEX-LLM `optimiz ## Requirements To run these examples with IPEX-LLM on Intel GPUs, we have some recommended requirements for your machine, please refer to [here](../../../README.md#requirements) for more information. -**Important: According to [Mistral Troubleshooting](https://huggingface.co/mistralai/Mistral-7B-v0.1#troubleshooting), please make sure you have installed `transformers==4.34.0` to run the example.** ## Example: Predict Tokens using `generate()` API In the example [generate.py](./generate.py), we show a basic use case for a Mistral model to predict the next N tokens using `generate()` API, with IPEX-LLM INT4 optimizations on Intel GPUs. @@ -16,9 +15,6 @@ conda create -n llm python=3.11 conda activate llm # below command will install intel_extension_for_pytorch==2.1.10+xpu as default pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/ - -# Refer to https://huggingface.co/mistralai/Mistral-7B-v0.1#troubleshooting, please make sure you are using a stable version of Transformers, 4.34.0 or newer. -pip install transformers==4.34.0 ``` #### 1.2 Installation on Windows @@ -29,9 +25,6 @@ conda activate llm # below command will install intel_extension_for_pytorch==2.1.10+xpu as default pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/ - -# Refer to https://huggingface.co/mistralai/Mistral-7B-v0.1#troubleshooting, please make sure you are using a stable version of Transformers, 4.34.0 or newer. -pip install transformers==4.34.0 ``` ### 2. Configures OneAPI environment variables for Linux diff --git a/python/llm/example/GPU/PyTorch-Models/Model/replit/README.md b/python/llm/example/GPU/PyTorch-Models/Model/replit/README.md index 4938682a..3bfbf245 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/replit/README.md +++ b/python/llm/example/GPU/PyTorch-Models/Model/replit/README.md @@ -15,7 +15,7 @@ conda activate llm # below command will install intel_extension_for_pytorch==2.1.10+xpu as default pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/ -pip install "transformers<4.35" +pip install transformers<=4.33.3 ``` #### 1.2 Installation on Windows @@ -26,6 +26,8 @@ conda activate llm # below command will install intel_extension_for_pytorch==2.1.10+xpu as default pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/ + +pip install transformers<=4.33.3 ``` ### 2. Configures OneAPI environment variables for Linux diff --git a/python/llm/example/GPU/PyTorch-Models/Model/solar/README.md b/python/llm/example/GPU/PyTorch-Models/Model/solar/README.md index 2b718cd4..4d157d19 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/solar/README.md +++ b/python/llm/example/GPU/PyTorch-Models/Model/solar/README.md @@ -14,8 +14,6 @@ conda create -n llm python=3.11 conda activate llm # below command will install intel_extension_for_pytorch==2.1.10+xpu as default pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/ - -pip install transformers==4.35.2 # required by SOLAR ``` #### 1.2 Installation on Windows @@ -26,8 +24,6 @@ conda activate llm # below command will install intel_extension_for_pytorch==2.1.10+xpu as default pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/ - -pip install transformers==4.35.2 # required by SOLAR ``` ### 2. Configures OneAPI environment variables for Linux diff --git a/python/llm/example/GPU/PyTorch-Models/Model/yi/README.md b/python/llm/example/GPU/PyTorch-Models/Model/yi/README.md index b48b9532..2b500175 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/yi/README.md +++ b/python/llm/example/GPU/PyTorch-Models/Model/yi/README.md @@ -1,5 +1,5 @@ # Yi -In this directory, you will find examples on how you could use IPEX-LLM `optimize_model` API on Yi models on [Intel GPUs](../../../README.md). For illustration purposes, we utilize the [01-ai/Yi-6B](https://huggingface.co/01-ai/Yi-6B) as a reference Yi model. +In this directory, you will find examples on how you could use IPEX-LLM `optimize_model` API on Yi models on [Intel GPUs](../../../README.md). For illustration purposes, we utilize the [01-ai/Yi-6B](https://huggingface.co/01-ai/Yi-6B) and [01-ai/Yi-6B-Chat](https://huggingface.co/01-ai/Yi-1.5-6B-Chat) as reference Yi models. ## 0. Requirements To run these examples with IPEX-LLM on Intel GPUs, we have some recommended requirements for your machine, please refer to [here](../../../README.md#requirements) for more information. @@ -112,7 +112,7 @@ python ./generate.py In the example, several arguments can be passed to satisfy your requirements: -- `--repo-id-or-model-path REPO_ID_OR_MODEL_PATH`: argument defining the huggingface repo id for the Yi model (e.g. `01-ai/Yi-6B`) to be downloaded, or the path to the huggingface checkpoint folder. It is default to be `'01-ai/Yi-6B'`. +- `--repo-id-or-model-path REPO_ID_OR_MODEL_PATH`: argument defining the huggingface repo id for the Yi model (e.g. `01-ai/Yi-6B` and `01-ai/Yi-6B-Chat`) to be downloaded, or the path to the huggingface checkpoint folder. It is default to be `'01-ai/Yi-6B-Chat'`. - `--prompt PROMPT`: argument defining the prompt to be infered (with integrated prompt format for chat). It is default to be `'AI是什么？'`. - `--n-predict N_PREDICT`: argument defining the max number of tokens to predict. It is default to be `32`. @@ -127,3 +127,13 @@ AI是什么？ AI是什么？ 人工智能（Artificial Intelligence），英文缩写为AI。它是研究、开发用于模拟、延伸和扩展人的智能的理论、方法、技术及 ``` + +#### [01-ai/Yi-6B-Chat](https://huggingface.co/01-ai/Yi-6B-Chat) +```log +Inference time: xxxx s +-------------------- Prompt -------------------- +AI是什么？ +-------------------- Output -------------------- +AI是什么？ +人工智能（Artificial Intelligence, AI）是计算机科学的一个分支，它研究如何让计算机模拟人类的智能行为。人工智能可以通过模仿人类的思维过程和 +``` \ No newline at end of file diff --git a/python/llm/example/GPU/PyTorch-Models/Model/yi/generate.py b/python/llm/example/GPU/PyTorch-Models/Model/yi/generate.py index 31256cda..871f5f4f 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/yi/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/yi/generate.py @@ -26,7 +26,7 @@ YI_PROMPT_FORMAT = "{prompt}" if __name__ == '__main__': parser = argparse.ArgumentParser(description='Predict Tokens using `generate()` API for Yi model') - parser.add_argument('--repo-id-or-model-path', type=str, default="01-ai/Yi-6B", + parser.add_argument('--repo-id-or-model-path', type=str, default="01-ai/Yi-6B-Chat", help='The huggingface repo id for the Yi model to be downloaded' ', or the path to the huggingface checkpoint folder') parser.add_argument('--prompt', type=str, default="AI是什么？",