allenai/Llama-3.1-Tulu-3-8B-DPO
Full fine-tune vs allenai/Llama-3.1-Tulu-3-8B-SFT. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 11/65, MLP 96/96, Attention 128/128, lm_head 1/1
6 derivatives checked
- allenai/Llama-3.1-Tulu-3-8B: Full fine-tune
- bartowski/Llama-3.1-Tulu-3-8B-DPO-GGUF: Same weights, converted
- allenai/Llama-3.1-Tulu-3.1-8B: Full fine-tune
- mradermacher/Llama-3.1-Tulu-3-8B-DPO-i1-GGUF: Quantization
- QuantFactory/Llama-3.1-Tulu-3-8B-GGUF: Full fine-tune
- mradermacher/Llama-3.1-Tulu-3-8B-DPO-GGUF: Same weights, converted