nlpguy/amdchess-v9

Full fine-tune vs amd/AMD-Llama-135m. Fine-tune: 100% of the weights changed, across 12 of 12 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 25/25, MLP 36/36, Attention 48/48

1 derivatives checked

• mradermacher/amdchess-v9-GGUF: Same weights, converted

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse