KaiChen1998/RACRO-7B-CRO
Partial fine-tune vs Qwen/Qwen2.5-VL-7B-Instruct. Partial change: 87% of the weights changed (attention, embeddings, mlp, norms), in 32 of 32 layers.
Tensors changed: Embeddings 1/2, Norms 57/122, MLP 279/280, Attention 324/324, lm_head 0/1
2 derivatives checked
- mradermacher/RACRO-7B-CRO-i1-GGUF: Quantization (fewer layers)
- mradermacher/RACRO-7B-CRO-GGUF: Same weights, converted (fewer layers)