Hugging Face's logo

NoorNizar
/
Meta-Llama-3-8B-Instruct-WINT4

Text Generation
Transformers
Safetensors
llama
llmcompressor
quantization
wint4
conversational
text-generation-inference
8-bit precision
compressed-tensors
Model card Files Community
Meta-Llama-3-8B-Instruct-WINT4 / tokenizer_config.json

Commit History

Upload 4-bit int quantized model via script
7b76fa0
verified

NoorNizar commited on