deepcogito/cogito-v2-preview-llama-70B
Full fine-tune vs meta-llama/Llama-3.1-70B. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, Norms 161/161, MLP 240/240, Attention 320/320, lm_head 1/1
6 derivatives checked
- unsloth/cogito-v2-preview-llama-70B-GGUF: Same weights, converted
- bartowski/deepcogito_cogito-v2-preview-llama-70B-GGUF: Quantization
- mradermacher/cogito-v2-preview-llama-70B-i1-GGUF: Quantization
- mradermacher/cogito-v2-preview-llama-70B-GGUF: Quantization
- lmstudio-community/cogito-v2-preview-llama-70B-GGUF: Quantization
- DevQuasar/deepcogito.cogito-v2-preview-llama-70B-GGUF: Quantization