Magpie-Align/Llama-3-8B-Magpie-Align-v0.3

Full fine-tune vs Magpie-Align/Llama-3-8B-Magpie-Align-SFT-v0.3. Fine-tune: 93% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 15/65, MLP 96/96, Attention 128/128, lm_head 1/1

1 derivatives checked

• tensorblock/Llama-3-8B-Magpie-Align-v0.3-GGUF: Quantization

On the Hub · Downloads on Model Pulse