joshycodes/qwen3-32b-commitments-v2-sdf

Full fine-tune vs joshycodes/qwen3-32b-commitments-sdf. Fine-tune: 98% of the weights changed, across 64 of 64 layers.

Tensors changed: lm_head 1/1, Embeddings 0/1, Norms 216/257, MLP 192/192, Attention 256/256

1 derivatives checked

• mradermacher/qwen3-32b-commitments-v2-sdf-GGUF: Quantization

On the Hub · Downloads on Model Pulse