huggingkot/Llama-3-8B-Instruct-abliterated-v2-bnb-4bit

Quantization vs QuixiAI/Llama-3-8B-Instruct-abliterated-v2. huggingkot/Llama-3-8B-Instruct-abliterated-v2-bnb-4bit is a quantized version of the other (U8/F16).

On the Hub · Downloads on Model Pulse