varox34/Llama-3-Mistral-v0.2-Instruct-slerp
Full fine-tune vs meta-llama/Meta-Llama-3-8B-Instruct. Fine-tune: 97% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 65/65, MLP 93/96, Attention 124/128
2 derivatives checked
- featherless-ai-quants/varox34-Llama-3-Mistral-v0.2-Instruct-slerp-GGUF: Quantization
- mradermacher/Llama-3-Mistral-v0.2-Instruct-slerp-GGUF: Same weights, converted