winglian/tulu3-dpo-8b-qat-v1-fixed

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

1 derivatives checked

• mradermacher/tulu3-dpo-8b-qat-v1-fixed-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse