allenai/Llama-3.1-Tulu-3-70B-DPO
Full fine-tune vs allenai/Llama-3.1-Tulu-3-70B-SFT. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, Norms 85/161, MLP 240/240, Attention 320/320, lm_head 1/1
4 derivatives checked
- bartowski/Llama-3.1-Tulu-3-70B-DPO-GGUF: Quantization
- mradermacher/Llama-3.1-Tulu-3-70B-DPO-i1-GGUF: Quantization
- allenai/Llama-3.1-Tulu-3-70B: Full fine-tune
- mradermacher/Llama-3.1-Tulu-3-70B-DPO-GGUF: Quantization