CogEvol/CogEvol-4B
Full fine-tune vs Qwen/Qwen3.5-4B. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/4, MLP 96/196, Attention 202/320, Norms 82/203
4 derivatives checked
- bartowski/CogEvol_CogEvol-4B-GGUF: Same weights, converted
- prithivMLmods/CogEvol-4B-GGUF: Same weights, converted
- mradermacher/CogEvol-4B-GGUF: Same weights, converted
- CogEvol/CogEvol-4B-Q4_K_M-GGUF: Quantization