pixas/DECS_7B

Partial fine-tune vs deepseek-ai/DeepSeek-R1-Distill-Qwen-7B. Partial change: 85% of the weights changed (attention, mlp, norms), in 28 of 28 layers.

Tensors changed: Embeddings 0/1, Attention 196/196, MLP 83/84, Norms 39/57, lm_head 0/1

2 derivatives checked

• mradermacher/DECS_7B-i1-GGUF: Quantization
• mradermacher/DECS_7B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse