NovoCode/Metabird-7b-DPO

Full fine-tune vs ConvexAI/Metabird-7B. Fine-tune: 99% of the weights changed, across 32 of 32 layers.

Tensors changed: MLP 96/96, Embeddings 0/1, Norms 13/65, Attention 128/128, lm_head 1/1

1 derivatives checked

• mradermacher/Metabird-7b-DPO-GGUF: Quantization

On the Hub · Downloads on Model Pulse