diff --git a/README.md b/README.md index 6331a58..0b87bd1 100644 --- a/README.md +++ b/README.md @@ -11,8 +11,8 @@ Read this in [English](README_en.md) ## 项目更新 -- 🔥🔥 **News**: ```2024/11/01```: 本仓库依赖进行升级，请更新`requirements.txt`中的依赖以保证正常运行模型。[glm-4-9b-chat-hf](https://huggingface.co/THUDM/glm-4-9b-chat-hf) 是适配 `transformers>=4.46` 的模型权重，使用 transforemrs 库中的 `GlmModel` 类实现。 -同时，[glm-4-9b-chat](https://huggingface.co/THUDM/glm-4-9b-chat), [glm-4v-9b](https://huggingface.co/THUDM/glm-4v-9b) 中的 `tokenzier_chatglm.py` 已经更新以适配最新版本的 `transforemrs`库。请前往 HuggingFace 更新文件。 +- 🔥🔥 **News**: ```2024/11/01```: 本仓库依赖进行升级，请更新`requirements.txt`中的依赖以保证正常运行模型。[glm-4-9b-chat-hf](https://huggingface.co/THUDM/glm-4-9b-chat-hf) 是适配 `transformers>=4.46.2` 的模型权重，使用 `transformers` 库中的 `GlmModel` 类实现。 +同时，[glm-4-9b-chat](https://huggingface.co/THUDM/glm-4-9b-chat), [glm-4v-9b](https://huggingface.co/THUDM/glm-4v-9b) 中的 `tokenzier_chatglm.py` 已经更新以适配最新版本的 `transformers`库。请前往 HuggingFace 更新文件。 - 🔥 **News**: ```2024/10/27```: 我们开源了 [LongReward](https://github.com/THUDM/LongReward)，这是一个使用 AI 反馈改进长上下文大型语言模型。 - 🔥 **News**: ```2024/10/25```: 我们开源了端到端中英语音对话模型 [GLM-4-Voice](https://github.com/THUDM/GLM-4-Voice)。 - 🔥 **News**: ```2024/09/05``` 我们开源了使LLMs能够在长上下文问答中生成细粒度引用的模型 [longcite-glm4-9b](https://huggingface.co/THUDM/LongCite-glm4-9b) 以及数据集 [LongCite-45k](https://huggingface.co/datasets/THUDM/LongCite-45k), 欢迎在 [Huggingface Space](https://huggingface.co/spaces/THUDM/LongCite) 在线体验。 diff --git a/README_en.md b/README_en.md index 19a7f3b..4940bec 100644 --- a/README_en.md +++ b/README_en.md @@ -11,8 +11,8 @@ - 🔥🔥 **News**: ```2024/11/01```: Dependencies have been updated in this repository. Please update the dependencies in `requirements.txt` to ensure the model runs correctly. The model weights - for [glm-4-9b-chat-hf](https://huggingface.co/THUDM/glm-4-9b-chat-hf) are compatible with `transformers>=4.46` and can - be implemented using the `GlmModel` class in the transformers library. Additionally, `tokenizer_chatglm.py` + for [glm-4-9b-chat-hf](https://huggingface.co/THUDM/glm-4-9b-chat-hf) are compatible with `transformers>=4.46.2` and can + be implemented using the `GlmModel` class in the `transformers` library. Additionally, `tokenizer_chatglm.py` in [glm-4-9b-chat](https://huggingface.co/THUDM/glm-4-9b-chat) and [glm-4v-9b](https://huggingface.co/THUDM/glm-4v-9b) has been updated for the latest version of `transformers`. Please update the files on HuggingFace. - 🔥 **News**: ```2024/10/27```: We have open-sourced [LongReward](https://github.com/THUDM/LongReward), a model that diff --git a/basic_demo/requirements.txt b/basic_demo/requirements.txt index cad81ed..f5fb147 100644 --- a/basic_demo/requirements.txt +++ b/basic_demo/requirements.txt @@ -1,7 +1,6 @@ -torch>=2.5.0 +torch>=2.5.1 # vLLM will use it torchvision>=0.20.0 -transformers>=4.46.0 -huggingface-hub>=0.25.1 +transformers>=4.46.2 sentencepiece>=0.2.0 jinja2>=3.1.4 pydantic>=2.9.2 @@ -11,13 +10,12 @@ numpy==1.26.4 # Need less than 2.0.0 accelerate>=1.0.1 sentence_transformers>=3.1.1 gradio==4.44.1 # web demo -openai>=1.51.0 # openai demo +openai>=1.54.0 # openai demo einops>=0.8.0 pillow>=10.4.0 sse-starlette>=2.1.3 -bitsandbytes>=0.43.3 # INT4 Loading +bitsandbytes>=0.44.1 # INT4 Loading -# vllm>=0.6.3 # using with VLLM Framework -# flash-attn>=2.6.3 # using with flash-attention 2 +vllm>=0.6.4.post1 # using with VLLM Framework # PEFT model, not need if you don't use PEFT finetune model. -# peft>=0.13.0 # Using with finetune model \ No newline at end of file +# peft>=0.14.0 # Using with finetune model \ No newline at end of file diff --git a/finetune_demo/requirements.txt b/finetune_demo/requirements.txt index 702c04c..6220079 100644 --- a/finetune_demo/requirements.txt +++ b/finetune_demo/requirements.txt @@ -1,7 +1,9 @@ jieba==0.42.1 datasets==2.20.0 -peft==0.12.2 +peft==0.14.0 deepspeed==0.14.4 nltk==3.8.1 rouge_chinese==1.0.3 -ruamel.yaml==0.18.6 \ No newline at end of file +ruamel.yaml==0.18.6 +typer==0.13.0 +tqdm==4.67.0 \ No newline at end of file