Takenoko12345678/Qwen3.5-0.8B-Japanese-SFT-v2
Partial fine-tune vs Qwen/Qwen3.5-0.8B. Partial change: 88% of the weights changed (attention, embeddings, mlp, norms), in 24 of 24 layers.
Tensors changed: Attention 147/216, Norms 73/129, Embeddings 1/4, MLP 72/124
4 derivatives checked
- mradermacher/Qwen3.5-0.8B-Japanese-SFT-v2-i1-GGUF: Quantization
- Takenoko12345678/Qwen3.5-0.8B-Japanese-SFT-v2-GGUF: Quantization
- mradermacher/Qwen3.5-0.8B-Japanese-SFT-v2-GGUF: Same weights, converted
- yuubinnkyoku/Qwen3.5-0.8B-Japanese-SFT-v2-Q4_0-GGUF: Quantization