Ted8000

Results 8 comments of Ted8000

How to fine tune vicuna-7b with A40

maybe you can remove flash_attn() ,

ERROR: [Errno 99] error while attempting to bind on address ('::1', 21001, 0, 0): cannot assign requested address

you shuold change locahost to 0.0.0.0, this can fix it

Playwright sync vs Async Error

anyone solved this?

accelerate does not support multi-gpu load int-8bit

same error

Fix #issues/320

yes, i find some special tokens decode would also cause stucked. All other requests are blocked.

[BUG]: 自从更新了 Version 1.8.19 引擎版本 1.36.0 磁力和bt都不动了

same

Could you add torch.onnx.export() in tools/export-onnx.py

yeal, where can i tranfer the model to onnx?

Am I fine-tuning gemma-2b or bge-reranker-v2-gemma?

> > @545999961 Can bge-reranker-v2.5-gemma2-lightweight be fine-tuned in this way？ > > bge-reranker-v2.5-gemma2-lightweight cannot be fine-tuned in this way, we will release the fine-tune code in the future. hello, Can...