Nexusflow/NexusRaven-V2-13B
Full fine-tune vs codellama/CodeLlama-13b-Instruct-hf. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Norms 81/81, MLP 120/120, Attention 160/160
5 derivatives checked
- TheBloke/NexusRaven-V2-13B-GGUF: Quantization
- QuantFactory/NexusRaven-V2-13B-GGUF: Quantization
- mradermacher/NexusRaven-V2-13B-i1-GGUF: Quantization
- DevQuasar-9/Nexusflow.NexusRaven-V2-13B-GGUF: Same weights, converted
- mradermacher/NexusRaven-V2-13B-GGUF: Quantization