deepcogito/cogito-v1-preview-qwen-32B
Full fine-tune vs Qwen/Qwen2.5-32B. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Norms 129/129, MLP 192/192, Attention 448/448
6 derivatives checked
- bartowski/deepcogito_cogito-v1-preview-qwen-32B-GGUF: Same weights, converted
- mradermacher/cogito-v1-preview-qwen-32B-i1-GGUF: Quantization
- mmnga/cogito-v1-preview-qwen-32B-gguf: Quantization
- DevQuasar-12/deepcogito.cogito-v1-preview-qwen-32B-GGUF: Same weights, converted
- mradermacher/cogito-v1-preview-qwen-32B-GGUF: Quantization
- lmstudio-community/cogito-v1-preview-qwen-32B-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.