chancharikm/CHAI_SFT_model_8b
Partial fine-tune vs Qwen/Qwen3-VL-8B-Instruct. Partial change: 88% of the weights changed (attention, embeddings, lm_head, mlp, norms), in 36 of 36 layers.
Tensors changed: Embeddings 1/4, Norms 136/261, MLP 120/232, Attention 144/252, lm_head 1/1
2 derivatives checked
- mradermacher/CHAI_SFT_model_8b-GGUF: Same weights, converted (fewer layers)
- Hibababab/CHAI_SFT_model_8b-GGUF: Same weights, converted (fewer layers)