jitsi
/

Llama-3.1-8B-Instruct-W8A8-Dynamic-Per-Token

8-bit precision

compressed-tensors

Model card Files Files and versions Community

Llama-3.1-8B-Instruct-W8A8-Dynamic-Per-Token

Commit History

Update with model quantized using llmcompressor 0.3.0

7ad6bbe
verified

quitrk commited on Dec 12, 2024

Upload quantized INT8 llama 3.1-8b-instruct model

c8d02a2
verified

quitrk commited on Dec 11, 2024

initial commit

4387660
verified

quitrk commited on Dec 11, 2024