Ecosyste.ms: Timeline
Browse the timeline of events for every public repo on GitHub. Data updated hourly from GH Archive.
YangWang92 created a branch on VPTQ/LLaMA-Factory
vptq/dev - Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
YangWang92 pushed 71 commits to main VPTQ/LLaMA-Factory
- Increase shm_size to 16GB in docker-compose.yml to optimize shared memory allocation for large-scale model fine-tunin... 6441490
- Support llama3.2vl. 3f2c056
- Tiny fix. 8372c5e
- Linter. b1e43e5
- fix inputs 446441f
- add forbidden modules df47737
- Merge pull request #5555 from marko1616/feat/llama3.2vl Support llama3.2 vision e68ef89
- fix ci b52c383
- Merge pull request #6120 from hiyouga/hiyouga/fix_ci [test] fix ci 5f310d9
- update readme a89ad72
- Merge pull request #6121 from hiyouga/hiyouga/readme [readme] update readme f2bfa80
- fix qwen2vl vllm infer fa50fc4
- Merge pull request #6123 from hiyouga/hiyouga/fix_qwen2vl_vllm [inference] fix qwen2vl vllm infer 0ce173e
- release v0.9.1 d622f8f
- fix cli 8792d78
- fix vllm 13ee1f5
- Merge pull request #6125 from hiyouga/hiyouga/fix_cli [cli] remove shell=True in cli 57953c8
- Merge pull request #6010 from XYZliang/fix-#4316 Increase shm_size to 16GB in docker-compose.yml 8e9f461
- Merge pull request #6126 from hiyouga/hiyouga/fix_vllm [inference] fix vllm 07059a7
- Merge pull request #6124 from hiyouga/hiyouga/release [release] release v0.9.1 18daf10
- and 51 more ...
YangWang92 created a comment on a pull request on microsoft/VPTQ
Yes, indeed there are some issues with our format and my code management. I will continue to improve. Thank you!
YangWang92 created a review comment on a pull request on microsoft/VPTQ
No worries! We appreciate your interest in our project. Feel free to offer any suggestions you might have; we welcome all kinds of feedback. :)
YangWang92 created a review comment on a pull request on microsoft/VPTQ
Hi @wejoncy, can you help to check this pull request? Thanks!
YangWang92 created a comment on a pull request on microsoft/VPTQ
Could you please provide any additional suggestions for our VPTQ project? Are there any areas where we need to make improvements?
YangWang92 pushed 2 commits to wy/hessian YangWang92/quip-sharp
YangWang92 closed a pull request on YangWang92/quip-sharp
Add support for NV-Embed model
Add Hessian computation script for NV-Embed. Adds a separate Hessian computation script for NV-Embed. I added a new script even though it is almost identical to the llama one due to lack of resourc...
YangWang92 pushed 1 commit to algorithm microsoft/VPTQ
- Adds nvembed model to quantization algorithm (#139) Add support for quantizing the NV-Embed model using VPTQ. Benchm... 441196f
YangWang92 closed a pull request on microsoft/VPTQ
Adds nvembed model to quantization algorithm
Add support for quantizing the NV-Embed model using VPTQ. Benchmarked using MTEB to evaluate performance against the `bfloat16` version. Current benchmarks are based on a single task, further testi...
YangWang92 created a comment on a pull request on microsoft/VPTQ
Thanks for your contribution! I will mergeit into the main branch and release a new version on PyPI.
YangWang92 created a comment on an issue on microsoft/VPTQ
fixed in https://github.com/microsoft/VPTQ/pull/138 Thanks!
YangWang92 closed an issue on microsoft/VPTQ
Colab demo: AttributeError: 'Qwen2Config' object has no attribute 'quant_config'
When running colab demo on https://colab.research.google.com/github/microsoft/VPTQ/blob/main/notebooks/vptq_example.ipynb , I encountered `AttributeError: 'Qwen2Config' object has no attribute 'qua...