allenai/Llama-3.1-Tulu-3-70B
Full fine-tune vs allenai/Llama-3.1-Tulu-3-70B-DPO. Fine-tune: 97% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 0/1, Norms 59/161, MLP 240/240, Attention 318/320, lm_head 0/1
7 derivatives checked
- bartowski/Llama-3.1-Tulu-3-70B-GGUF: Quantization
- mradermacher/Llama-3.1-Tulu-3-70B-i1-GGUF: Quantization
- lmstudio-community/Llama-3.1-Tulu-3-70B-GGUF: Quantization
- unsloth/Llama-3.1-Tulu-3-70B-GGUF: Quantization
- mradermacher/Llama-3.1-Tulu-3-70B-GGUF: Quantization
- nitky/Llama-3.1-SuperSwallow-70B-Instruct-v0.1: Full fine-tune
- nitky/Llama-3.3-SuperSwallow-70B-Instruct-v0.1: Full fine-tune