tokyotech-llm/Qwen3-Swallow-30B-A3B-RL-v0.2
Full fine-tune vs tokyotech-llm/Qwen3-Swallow-30B-A3B-SFT-v0.2. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 127/193, MLP 2613/2613, Attention 192/192, lm_head 1/1
4 derivatives checked
- mmnga-o/Qwen3-Swallow-30B-A3B-RL-v0.2-gguf: Quantization
- tokyotech-llm/Medical-Qwen3-Swallow-30B-A3B: Full fine-tune
- yuseiito/Qwen3-Swallow-30B-A3B-RL-v0.2-GGUF: Same weights, converted
- sasa2000/Qwen3-Swallow-30B-A3B-RL-v0.2-heretic: Abliterated