dots-studio/dots.llm1.inst

Full fine-tune vs dots-studio/dots.llm1.base. Fine-tune: 100% of the weights changed, across 62 of 62 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 145/249, MLP 2440/2501, Attention 248/248

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

On the Hub · Downloads on Model Pulse