reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT

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

Tensors changed: Embeddings 0/1, Norms 78/113, MLP 84/84, Attention 112/112, lm_head 1/1

2 derivatives checked

• reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT-GGUF: Same weights, converted
• tinyopsec/Qwen3-1.7B-Coder-Distilled-SFT-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse