nvidia/Llama-3.3-Nemotron-70B-Select
Full fine-tune vs meta-llama/Llama-3.3-70B-Instruct. Fine-tune: 99% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 0/1, Norms 136/161, MLP 240/240, Attention 320/320, lm_head 1/1
4 derivatives checked
- mradermacher/Llama-3.3-Nemotron-70B-Select-i1-GGUF: Quantization
- featherless-ai-quants/nvidia-Llama-3.3-Nemotron-70B-Select-GGUF: Quantization
- DevQuasar-11/nvidia.Llama-3.3-Nemotron-70B-Select-GGUF: Same weights, converted
- mradermacher/Llama-3.3-Nemotron-70B-Select-GGUF: Quantization