sethuiyer/Medichat-V2-Llama3-8B
Full fine-tune vs Locutusque/Llama-3-Hercules-5.0-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1
1 derivatives checked
- mradermacher/Medichat-V2-Llama3-8B-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.