grimjim/llama-3-experiment-v1-9B
Partial fine-tune vs meta-llama/Meta-Llama-3-8B-Instruct. Partial change: 54% of the weights changed (attention, mlp, norms), in 20 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 40/65, MLP 60/96, Attention 80/128, lm_head 0/1
4 derivatives checked
- mradermacher/llama-3-experiment-v1-9B-GGUF: Same weights, converted
- mradermacher/llama-3-experiment-v1-9B-i1-GGUF: Quantization
- grimjim/llama-3-experiment-v1-9B-GGUF: Quantization
- nicoboss/llama-3-experiment-v1-9B-Uncensored: LoRA-style