想請問可不可以使用量化過後的中文模型(GGUF格式)來訓練 #471
james60415
started this conversation in
General
Replies: 1 comment 3 replies
-
GGUF是llama.cpp独有格式,与训练脚本(基于transformers、PyTorch)不兼容。 |
Beta Was this translation helpful? Give feedback.
3 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
目前使用v100 16G顯示卡按照wiki的預訓練腳本訓練7B的中文模型會OOM,所以想改使用8bit或6bit量化的GGUF模型來訓練。想問可以這樣訓練嗎,如果可以的訓練的話訓練步驟按照llama.cpp的手冊做可以嗎
Beta Was this translation helpful? Give feedback.
All reactions