nex-agi/DeepSeek-V3.1-Nex-N1.1

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 1/1, Attention 620/620, Norms 199/251, MLP 2064/2123, lm_head 1/1, other 1/1

1 derivatives checked

• mradermacher/DeepSeek-V3.1-Nex-N1.1-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse