HF1BitLLM/Llama3-8B-1.58-100B-tokens

Quantization vs meta-llama/Meta-Llama-3-8B-Instruct. HF1BitLLM/Llama3-8B-1.58-100B-tokens is a quantized version of the other (BF16/U8).

1 derivatives checked

• brunopio/Llama3-8B-1.58-100B-tokens-GGUF: Identical copy

5 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse