deepcogito/cogito-v1-preview-llama-3B
Full fine-tune vs meta-llama/Llama-3.2-3B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 112/112
7 derivatives checked
- bartowski/deepcogito_cogito-v1-preview-llama-3B-GGUF: Same weights, converted
- DevQuasar-13/deepcogito.cogito-v1-preview-llama-3B-GGUF: Same weights, converted
- prithivMLmods/cogito-v1-preview-llama-3B-f32-GGUF: Same weights, converted
- gabrielmtzcarrillo/deepcogito-cogito-v1-preview-llama-3B-heretic-gguf: Abliterated
- lmstudio-community/cogito-v1-preview-llama-3B-GGUF: Quantization
- MaziyarPanahi/cogito-v1-preview-llama-3B-GGUF: Same weights, converted
- mlx-community/deepcogito-cogito-v1-preview-llama-3B-4bit: Quantization