nvidia/OpenMath2-Llama3.1-70B

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

5 derivatives checked

• mradermacher/OpenMath2-Llama3.1-70B-i1-GGUF: Quantization
• featherless-ai-quants/nvidia-OpenMath2-Llama3.1-70B-GGUF: Quantization
• mradermacher/OpenMath2-Llama3.1-70B-GGUF: Quantization
• DevQuasar-5/nvidia.OpenMath2-Llama3.1-70B-GGUF: Quantization
• tensorblock/OpenMath2-Llama3.1-70B-GGUF: Quantization

On the Hub · Downloads on Model Pulse