出个4bit量化版本吧
#9
by
piboye
- opened
出个4bit量化版本吧
雀食
This comment has been hidden
出个4bit量化版本吧
Found this one but hasn't tested it yet:
https://huggingface.co/gaianet/gte-Qwen1.5-7B-instruct-GGUF
出个4bit量化版本吧
Found this one but hasn't tested it yet:
https://huggingface.co/gaianet/gte-Qwen1.5-7B-instruct-GGUF
Ive tried earlier, can not run with llama.cpp, error goes like : llama_add_eos_token(model) != 1