code-critic-model/Qwen3-4B-Critic-SFT-DPO

Full fine-tune vs code-critic-model/Qwen3-4B-Critic-SFT. Fine-tune: 100% of the weights changed, across 36 of 36 layers.

Tensors changed: Embeddings 1/1, Norms 87/145, MLP 108/108, Attention 144/144

1 derivatives checked

• flammafex/Qwen3-4B-High-Level-Critic-SFT-DPO-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse