diff --git a/README.md b/README.md index 50ee4c0..c6600af 100644 --- a/README.md +++ b/README.md @@ -10,10 +10,15 @@ Read this in [English](README_en.md) ## 项目更新 -- 🔥🔥 **News**: ```2024/07/24```: 我们发布了与长文本相关的最新技术解读，关注 [这里](https://medium.com/@ChatGLM/glm-long-scaling-pre-trained-model-contexts-to-millions-caa3c48dea85) 查看我们在训练 GLM-4-9B 开源模型中关于长文本技术的技术报告。 -- 🔥 **News**: ``2024/7/16``: GLM-4-9B-Chat 模型依赖的` transformers`版本升级到 `4.42.4`, 请更新模型配置文件并参考 `basic_demo/requirements.txt` 更新依赖。 + +- 🔥🔥 **News**: ```2024/08/12```: GLM-4-9B-Chat 模型依赖的`transformers`版本升级到 `4.44.0`，请重新拉取除模型权重( + `*.safetensor` 文件 和 `tokenizer.model`)外的文件并参考 `basic_demo/requirements.txt` 严格更新依赖。 +- 🔥 **News**: ```2024/07/24```: + 我们发布了与长文本相关的最新技术解读，关注 [这里](https://medium.com/@ChatGLM/glm-long-scaling-pre-trained-model-contexts-to-millions-caa3c48dea85) + 查看我们在训练 GLM-4-9B 开源模型中关于长文本技术的技术报告。 - 🔥 **News**: ``2024/7/9``: GLM-4-9B-Chat - 模型已适配 [Ollama](https://github.com/ollama/ollama),[Llama.cpp](https://github.com/ggerganov/llama.cpp)，您可以在[PR](https://github.com/ggerganov/llama.cpp/pull/8031) 查看具体的细节。 + 模型已适配 [Ollama](https://github.com/ollama/ollama),[Llama.cpp](https://github.com/ggerganov/llama.cpp) + ，您可以在[PR](https://github.com/ggerganov/llama.cpp/pull/8031) 查看具体的细节。 - 🔥 **News**: ``2024/7/1``: 我们更新了 GLM-4V-9B 的微调，您需要更新我们的模型仓库的运行文件和配置文件， 以支持这个功能，更多微调细节 (例如数据集格式，显存要求)，请前往 [查看](finetune_demo)。 - 🔥 **News**: ``2024/6/28``: 我们与英特尔技术团队合作，改进了 GLM-4-9B-Chat 的 ITREX 和 OpenVINO 部署教程。您可以使用英特尔 diff --git a/README_en.md b/README_en.md index 6d07987..936e61a 100644 --- a/README_en.md +++ b/README_en.md @@ -8,11 +8,14 @@ </p> ## Update -- 🔥🔥 **News**: ```2024/07/24```: we released the latest technical interpretation related to long texts. Check -out [here](https://medium.com/@ChatGLM/glm-long-scaling-pre-trained-model-contexts-to-millions-caa3c48dea85) to view our -technical report on long context technology in the training of the open-source GLM-4-9B model. -- 🔥 **News**: ``2024/7/16``: The ` transformers` version that the GLM-4-9B-Chat model depends on has been upgraded -to `4.42.4`. Please update the model configuration file and refer to `basic_demo/requirements.txt` to update the dependencies. + +- 🔥🔥 **News**: ```2024/08/12```: The `transformers` version required for the GLM-4-9B-Chat model has been upgraded + to `4.44.0`. Please re-download all files except for the model weights (`*.safetensor` files and `tokenizer.model`), + and strictly update the dependencies as per `basic_demo/requirements.txt`. +- 🔥 **News**: ```2024/07/24```: we released the latest technical interpretation related to long texts. Check + out [here](https://medium.com/@ChatGLM/glm-long-scaling-pre-trained-model-contexts-to-millions-caa3c48dea85) to view + our + technical report on long context technology in the training of the open-source GLM-4-9B model. - 🔥 **News**: ``2024/7/9``: The GLM-4-9B-Chat model has been adapted to [Ollama](https://github.com/ollama/ollama) and [Llama.cpp](https://github.com/ggerganov/llama.cpp), you can check the specific details in [PR](https://github.com/ggerganov/llama.cpp/pull/8031). diff --git a/basic_demo/requirements.txt b/basic_demo/requirements.txt index b688d52..932759e 100644 --- a/basic_demo/requirements.txt +++ b/basic_demo/requirements.txt @@ -1,22 +1,23 @@ -torch>=2.3.0 -torchvision>=0.18.0 -transformers>=4.42.4 -huggingface-hub>=0.24.0 +torch>=2.4.0 +torchvision>=0.19.0 +transformers==4.44.0 +huggingface-hub>=0.24.5 sentencepiece>=0.2.0 jinja2>=3.1.4 pydantic>=2.8.2 -timm>=1.0.7 +timm>=1.0.8 tiktoken>=0.7.0 -accelerate>=0.32.1 +numpy==1.26.4 # Need less than 2.0.0 +accelerate>=0.33.0 sentence_transformers>=3.0.1 -gradio>=4.38.1 # web demo -openai>=1.35.0 # openai demo +gradio>=4.41.0 # web demo +openai>=1.40.3 # openai demo einops>=0.8.0 pillow>=10.4.0 -sse-starlette>=2.1.2 -bitsandbytes>=0.43.1 # INT4 Loading +sse-starlette>=2.1.3 +bitsandbytes>=0.43.3 # INT4 Loading -# vllm>=0.5.2 -# flash-attn>=2.5.9 # using with flash-attention 2 +# vllm==0.5.4 # using with VLLM Framework +# flash-attn>=2.6.1 # using with flash-attention 2 # PEFT model, not need if you don't use PEFT finetune model. -# peft>=0.11.1 \ No newline at end of file +# peft>=0.12.2 # Using with finetune model \ No newline at end of file diff --git a/composite_demo/requirements.txt b/composite_demo/requirements.txt index c0d3133..ecc5919 100644 --- a/composite_demo/requirements.txt +++ b/composite_demo/requirements.txt @@ -3,13 +3,13 @@ ipykernel>=6.26.0 ipython>=8.18.1 jupyter_client>=8.6.0 -langchain>=0.2.10 -langchain-community>=0.2.9 -matplotlib>=3.9.0 -pymupdf>=1.24.5 +langchain>=0.2.12 +langchain-community>=0.2.11 +matplotlib>=3.9.1 +pymupdf>=1.24.9 python-docx>=1.1.2 python-pptx>=0.6.23 pyyaml>=6.0.1 requests>=2.31.0 -streamlit>=1.36.0 -zhipuai>=2.1.3 \ No newline at end of file +streamlit>=1.37.1 +zhipuai>=2.1.4 \ No newline at end of file diff --git a/finetune_demo/requirements.txt b/finetune_demo/requirements.txt index 4485eec..702c04c 100644 --- a/finetune_demo/requirements.txt +++ b/finetune_demo/requirements.txt @@ -1,7 +1,7 @@ -jieba>=0.42.1 -datasets>=2.20.0 -peft>=0.11.1 -deepspeed>=0.14.4 +jieba==0.42.1 +datasets==2.20.0 +peft==0.12.2 +deepspeed==0.14.4 nltk==3.8.1 -rouge_chinese>=1.0.3 -ruamel.yaml>=0.18.6 \ No newline at end of file +rouge_chinese==1.0.3 +ruamel.yaml==0.18.6 \ No newline at end of file