tokyotech-llm/Qwen3-Swallow-32B-SFT-v0.2
Full fine-tune vs tokyotech-llm/Qwen3-Swallow-32B-CPT-v0.2. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 1/1, Norms 247/257, MLP 192/192, Attention 256/256, lm_head 1/1
2 derivatives checked
- tokyotech-llm/Qwen3-Swallow-32B-RL-v0.2: Full fine-tune
- ultimatechris/Qwen3-Swallow-32B-SFT-v0.2-GGUF: Quantization