MMOPD/Qwen3-4B-OT3-2ep
Full fine-tune vs Qwen/Qwen3-4B-Base. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 142/145, MLP 108/108, Attention 144/144
8 derivatives checked
- MMOPD/Qwen3-4B-OT3-law: Full fine-tune
- MMOPD/Qwen3-4B-OT3-tau: Full fine-tune
- MMOPD/Qwen3-4B-OT3-tau2-2ep: Full fine-tune
- MMOPD/Qwen3-4B-OT3-tau2-1ep: Full fine-tune
- MMOPD/Qwen3-4B-OT3-tau2-3ep: Full fine-tune
- MMOPD/Qwen3-4B-OT3-medical: Full fine-tune
- MMOPD/Qwen3-4B-OT3-finance: Full fine-tune
- MMOPD/Qwen3-4B-OT3-if: Full fine-tune