AIR-hl/Mistral-7B-Base-WPO-bf16

Full fine-tune vs HuggingFaceH4/mistral-7b-sft-beta. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 13/65, MLP 96/96, Attention 128/128, lm_head 1/1

1 derivatives checked

• mradermacher/Mistral-7B-Base-WPO-bf16-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse