bjaidi
/

Meta-Llama-3-8B-Instruct-GPTQ-8-bit

Text Generation

text-generation-inference

8-bit precision

Model card Files Files and versions

Meta-Llama-3-8B-Instruct-GPTQ-8-bit

9.26 GB

1 contributor

History: 3 commits

bjaidi's picture

add tokenizer

f8a34a0 over 1 year ago