RavichandranJ/hacking-assistant

Partial fine-tune vs unsloth/llama-3-8b-bnb-4bit. Partial change: 2% of the weights changed (attention, mlp), in 32 of 32 layers.

Tensors changed: MLP 210/498, Attention 271/664, lm_head 0/1, Embeddings 0/1, Norms 0/65

On the Hub · Downloads on Model Pulse