Hugging Face's logo

NoorNizar
/
Meta-Llama-3-8B-Instruct-WINT8

Text Generation
Transformers
Safetensors
llama
llmcompressor
quantization
wint8
conversational
text-generation-inference
8-bit precision
compressed-tensors
Model card Files Community
Meta-Llama-3-8B-Instruct-WINT8 / recipe.yaml

Commit History

Upload 8-bit quantized weights via llmcompressor script
5859792
verified

NoorNizar commited on