jiazhengli/Pythia-2.8B-HH-RLHF-Iterative-SamPO

Full fine-tune vs EleutherAI/pythia-2.8b. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Norms 130/130, Attention 128/128, MLP 128/128

2 derivatives checked

• mradermacher/Pythia-2.8B-HH-RLHF-Iterative-SamPO-i1-GGUF: Quantization
• mradermacher/Pythia-2.8B-HH-RLHF-Iterative-SamPO-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse