reaperdoesntknow/DistilQwen3-1.7B-uncensored

Partial fine-tune vs reaperdoesntknow/Qwen3-1.7B-Distilled-30B-A3B. Partial change: 85% of the weights changed (attention, lm_head, mlp, norms), in 28 of 28 layers.

Tensors changed: lm_head 1/1, Embeddings 0/1, Norms 85/113, MLP 84/84, Attention 112/112

2 derivatives checked

• reaperdoesntknow/DistilQwen3-1.7B-uncensored-GGUF: Same weights, converted
• mradermacher/DistilQwen3-1.7B-uncensored-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse