sparrow18/DeepSeek-V3.1-Terminus

Full fine-tune vs deepseek-ai/DeepSeek-V3.1-Base. Fine-tune: 100% of the weights changed, across 62 of 62 layers.

Tensors changed: Embeddings 2/2, Attention 578/620, Norms 252/252, MLP 2046/2123, lm_head 1/1, other 2/2

On the Hub · Downloads on Model Pulse