nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
Full fine-tune vs meta-llama/Llama-3.1-70B-Instruct. Fine-tune: 99% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 0/1, Norms 88/161, MLP 240/240, Attention 320/320, lm_head 1/1
22 derivatives checked
- bartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF: Quantization
- mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF: Quantization
- backyardai/Llama-3.1-Nemotron-70B-Instruct-GGUF: Same weights, converted
- mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF: Quantization
- mlx-community/nvidia_Llama-3.1-Nemotron-70B-Instruct-HF_4bit: Quantization
- lmstudio-community/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF: Quantization
- second-state/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF: Same weights, converted
- featherless-ai-quants/nvidia-Llama-3.1-Nemotron-70B-Instruct-HF-GGUF: Quantization
- gaianet/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF: Same weights, converted
- mlx-community/Llama-3.1-Nemotron-70B-Instruct-HF-bf16: Same weights, repacked
- mlx-community/Llama-3.1-Nemotron-70B-Instruct-HF-4bit: Quantization
- mlx-community/Llama-3.1-Nemotron-70B-Instruct-HF-8bit: Quantization
- DevQuasar-5/nvidia.Llama-3.1-Nemotron-70B-Instruct-HF-GGUF: Quantization
- mlx-community/Llama-3.1-Nemotron-70B-Instruct-HF: Same weights, converted
- RedHatAI/Llama-3.1-Nemotron-70B-Instruct-HF-FP8-dynamic: Quantization
- joshmiller656/Llama-3.1-Nemotron-70B-Instruct-AWQ-INT4: Quantization
- crestf411/L3.1-nemotron-sunfall-v0.7.0: LoRA-style
- ssmits/Llama-3.1-Nemotron-92B-Instruct-HF-late: Partial fine-tune
- ssmits/Llama-3.1-Nemotron-92B-Instruct-HF-early: Partial fine-tune
- unsloth/Llama-3.1-Nemotron-70B-Instruct: Identical copy
- OpenBuddy/openbuddy-nemotron-70b-v23.1-131k: Full fine-tune
- Ppoyaa/MythoNemo-L3.1-70B-v1.0: LoRA-style
5 other repos hold byte-for-byte identical weight files.