FlameF0X/ChessSLM-RL

Full fine-tune vs FlameF0X/ChessSLM. Fine-tune: 99% of the weights changed, across 6 of 6 layers.

Tensors changed: Attention 24/24, Norms 12/26, MLP 24/24, Embeddings 1/2

On the Hub · Downloads on Model Pulse