allenai/llama-3-tulu-2-70b
Full fine-tune vs meta-llama/Meta-Llama-3-70B. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, Norms 160/161, MLP 240/240, Attention 320/320, lm_head 1/1
4 derivatives checked
- mradermacher/llama-3-tulu-2-70b-i1-GGUF: Quantization
- mradermacher/llama-3-tulu-2-70b-GGUF: Quantization
- allenai/llama-3-tulu-2-dpo-70b: Full fine-tune
- allenai/llama-3-tulu-2-70b-uf-mean-rm: Full fine-tune