tokyotech-llm/Qwen3-Swallow-8B-SFT-v0.2
Full fine-tune vs tokyotech-llm/Qwen3-Swallow-8B-CPT-v0.2. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 143/145, MLP 108/108, Attention 144/144, lm_head 1/1
3 derivatives checked
- tokyotech-llm/Qwen3-Swallow-8B-RL-v0.2: Full fine-tune
- mmnga-o/Qwen3-Swallow-8B-SFT-v0.2-gguf: Quantization
- tatsuyaaaaaaa/Qwen3-Swallow-8B-SFT-v0.2-gguf: Same weights, converted