joshycodes/qwen3-14b-commitments-sdf

Full fine-tune vs Qwen/Qwen3-14B. Fine-tune: 95% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 0/1, Norms 140/161, MLP 120/120, Attention 160/160, lm_head 1/1

2 derivatives checked

• mradermacher/qwen3-14b-commitments-sdf-GGUF: Quantization
• joshycodes/qwen3-14b-commitments-v2-sdf: Full fine-tune

On the Hub · Downloads on Model Pulse