deepcogito/cogito-v1-preview-qwen-14B
Full fine-tune vs Qwen/Qwen2.5-14B. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Norms 97/97, MLP 144/144, Attention 336/336
7 derivatives checked
- bartowski/deepcogito_cogito-v1-preview-qwen-14B-GGUF: Same weights, converted
- mradermacher/cogito-v1-preview-qwen-14B-i1-GGUF: Quantization
- DevQuasar-12/deepcogito.cogito-v1-preview-qwen-14B-GGUF: Same weights, converted
- infohound/cogito-14b-voice-GGUF: Quantization
- mmnga/cogito-v1-preview-qwen-14B-gguf: Quantization
- mradermacher/cogito-v1-preview-qwen-14B-GGUF: Quantization
- lmstudio-community/cogito-v1-preview-qwen-14B-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.