hydra-project/CerebrumDolphin-2.0-Mistral-7B-v0.2

Full fine-tune vs Locutusque/OpenCerebrum-2.0-7B. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 14/65, MLP 93/96, Attention 124/128, lm_head 1/1

1 derivatives checked

• mradermacher/CerebrumDolphin-2.0-Mistral-7B-v0.2-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse