Ecosyste.ms: Timeline
Browse the timeline of events for every public repo on GitHub. Data updated hourly from GH Archive.
sixsixcoder created a review comment on a pull request on THUDM/GLM-4
Yes, I tested it on vllm=0.6.3.post2, and these parameters have been removed
sixsixcoder opened a pull request on THUDM/GLM-4
Support for GLM-4-9B-Chat-hf and GLM-4v-9B models on vLLM >= 0.6.3 and transformers >= 4.46.0
Support for GLM-4-9B-Chat-hf and GLM-4v-9B models on vLLM >= 0.6.3 and transformers >= 4.46.0, the major changes are in`GLM-4/basic_demo`
sixsixcoder pushed 7 commits to main sixsixcoder/GLM-4
- Update finetune.py 上一个commit在配置文件添加了freezeV选项，但在finetune.py中没有支持。https://github.com/THUDM/GLM-4/commit/1c2676415c213... f6ee34e
- Merge pull request #585 from sixsixcoder/main Add GLM-4v-9B model support for vllm framework 5142bdb
- Merge pull request #563 from huolongguo1O/patch-1 解决finetune.py在加载配置文件时的错误 4e9b473
- Update README.md 9cd635a
- transforemrs>=4.46 support c2c28bc
- update for transformers 4.46 94776fb
- remove wrong path 6bf9f85
sixsixcoder created a comment on an issue on THUDM/GLM-4
This model file can be used to emdedding images. https://huggingface.co/THUDM/glm-4v-9b/blob/main/visual.py
sixsixcoder closed an issue on THUDM/GLM-4
LlamaFactory lora微调glm4过拟合严重
### System Info / 系統信息 3090 x4 CentOS ### Who can help? / 谁可以帮助到您？ _No response_ ### Information / 问题信息 - [ ] The official example scripts / 官方的示例脚本 - [X] My own modified scripts / 我自己修改的脚本和任务...
sixsixcoder closed an issue on THUDM/GLM-4
glm-4v-9b支持在910B上部署么
### System Info / 系統信息 glm-4v-9b支持在910B上部署么 ### Who can help? / 谁可以帮助到您？ @Z ### Information / 问题信息 - [X] The official example scripts / 官方的示例脚本 - [ ] My own modified scripts / 我自己修改的脚本和任务 ###...
sixsixcoder closed an issue on THUDM/GLM-4
Need chat template when using vllm as an openai api compatible server with glm-4v-9b
### System Info / 系統信息 PyTorch version: 2.4.0+cu121 Is debug build: False CUDA used to build PyTorch: 12.1 ROCM used to build PyTorch: N/A OS: Ubuntu 22.04.3 LTS (x86_64) GCC version: (Ub...
sixsixcoder created a comment on an issue on THUDM/GLM-4
楼上是正解， > @Linlp 去掉glm_server.py里面的这一行。 ` "use_beam_search": False,` 我印象中好像还有别的参数也需要去掉，去掉之后你多运行几次试试。 > > 另外，我记得如果是vllm高版本的话，这行的`inputs=inputs`可能需要改为`prompt=inputs`。 `async for output in engine...
sixsixcoder created a comment on an issue on THUDM/GLM-4
建议你可以先把`glm-4v-9b`模型文件下载到本地，然后替换"THUDM/glm-4v-9b"为本地模型路径
sixsixcoder opened a pull request on THUDM/GLM-4-Voice
Support loading and launching web programs from vllm=0.6.3
Support loading and launching web programs from vllm=0.6.3
sixsixcoder pushed 1 commit to vllm063 sixsixcoder/GLM-4-Voice
- Support loading and starting web from vllm=0.6.3 bf1bb7d
sixsixcoder created a comment on an issue on THUDM/GLM-4
建议升级到transformers==4.44，我这边复线了你的问题的，升级后可以解决
sixsixcoder closed a pull request on sgl-project/sglang
Add GLM-4v Multimodal Model support for SGLang
<!-- Thank you for your contribution! We appreciate it. The following guidelines will help improve your pull request and facilitate feedback. If anything is unclear, don't hesitate to submit your p...
sixsixcoder closed an issue on THUDM/GLM-4
TypeError: ChatGLM4Tokenizer._pad() got an unexpected keyword argument 'padding_side'
### System Info / 系統信息 +-----------------------------------------------------------------------------+ | NVIDIA-SMI 470.129.06 Driver Version: 470.129.06 CUDA Version: 12.4 | |----------...