allenai/Llama-3.1-Tulu-3-70B-SFT
Full fine-tune vs meta-llama/Llama-3.1-70B. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Norms 157/161, MLP 240/240, Attention 320/320
4 derivatives checked
- bartowski/Llama-3.1-Tulu-3-70B-SFT-GGUF: Quantization
- mradermacher/Llama-3.1-Tulu-3-70B-SFT-i1-GGUF: Quantization
- allenai/Llama-3.1-Tulu-3-70B-DPO: Full fine-tune
- mradermacher/Llama-3.1-Tulu-3-70B-SFT-GGUF: Quantization