你可能會喜歡
We add some features to improve the GRPO training speed up to 200% based on the awesome work of TRL and Open-R1, check script here: github.com/modelscope/ms-… check wandb here: wandb.ai/tastelikefeet/…

SWIFT has supported the finetuning(VQA/Grounding/OCR/etc) of Qwen2-VL series models, check: github.com/modelscope/ms-…
We start a space in huggingface: huggingface.co/spaces/modelsc… meanwhile, we support peft 0.11.0 with hqq/eetq/vera/pissa training!
huggingface.co
Swift(LLM lightweight framework for fine-tuning and inference) - a Hugging Face Space by modelscope
Swift(LLM lightweight framework for fine-tuning and inference) - a Hugging Face Space by modelscope
Welcome to use quantized version of Yi1.5-6b/9b/34b! model can be found here: huggingface.co/modelscope
huggingface.co
modelscope (modelscope)
modelscope (modelscope)
SWIFT is an LLM/MLLM training framework from the ModelScope community and supports models like LLaMA3/Mistral/DeepSeek-VL/YI-VL/Qwen-VL/LLaVA. We have newly supported the EETQ and HQQ QLoRA training for LLM and MLLMs: github.com/modelscope/swi… @_akhaliq
We support the training of qwen2-110b models, use this script: github.com/modelscope/swi… to train!
United States 趨勢
- 1. D’Angelo 187K posts
- 2. Brown Sugar 15.5K posts
- 3. Black Messiah 7,314 posts
- 4. Voodoo 15.2K posts
- 5. Happy Birthday Charlie 120K posts
- 6. #PortfolioDay 9,791 posts
- 7. Powell 36.9K posts
- 8. How Does It Feel 7,099 posts
- 9. Osimhen 119K posts
- 10. Young Republicans 3,723 posts
- 11. Pentagon 97.6K posts
- 12. #BornOfStarlightHeeseung 81.6K posts
- 13. Alex Jones 27.7K posts
- 14. Neo-Soul 17K posts
- 15. Sandy Hook 11K posts
- 16. CJGJ N/A
- 17. Jill Scott 1,195 posts
- 18. Untitled 6,193 posts
- 19. Really Love 71.9K posts
- 20. World Cup 254K posts
你可能會喜歡
Something went wrong.
Something went wrong.