ChenWeiLi/MedLlama-3-8B_DARE

Full fine-tune vs johnsnowlabs/JSL-MedLlama-3-8B-v2.0. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

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

2 derivatives checked

• featherless-ai-quants/ChenWeiLi-MedLlama-3-8B_DARE-GGUF: Quantization
• mradermacher/MedLlama-3-8B_DARE-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse