ruggsea/Llama3-stanford-encyclopedia-philosophy-QA

Full fine-tune vs meta-llama/Meta-Llama-3-8B-Instruct. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128

2 derivatives checked

• mradermacher/Llama3-stanford-encyclopedia-philosophy-QA-i1-GGUF: Quantization
• mradermacher/Llama3-stanford-encyclopedia-philosophy-QA-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse