007ankit/JSL-MedLlama-3-8B-v1.0-Llama-3-8B-Hindi-Sathi-v0.1

Full fine-tune vs johnsnowlabs/JSL-MedLlama-3-8B-v1.0. 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