Echelon-AI/hindi-medbot-llama3

Full fine-tune vs Cognitive-Lab/LLama3-Gaja-Hindi-8B-v0.1. 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