Kunger
/

Sakura-13B-v0.11Pre-4Bit-AWQ-No-flash_attn

Text Generation

4-bit precision

Model card Files Files and versions Community

Sakura-13B-v0.11Pre-4Bit-AWQ-No-flash_attn / README.md

Kunger's picture

Update README.md

081c2d6 verified 3 months ago

|

raw history blame contribute delete

No virus

300 Bytes

metadata

license: cc-by-nc-sa-4.0

原始模型:Sakura-13B-LNovel-v0.11pre1

4Bit AWQ量化，未测试，不建议使用。

采用未安装flash_attn的环境进行量化

Intel-XPU测试用，该量化模型可能不适合所有人。