Edit model card

A bit of extremely minor tensor surgery on https://huggingface.co/cognitivecomputations/dolphin-2.9.1-mixtral-1x22b to unwrap the 1 expert Mixtral burrito and replace it with a Mistral tortilla.

Downloads last month
1
Safetensors
Model size
22.2B params
Tensor type
BF16
·
Inference API
Input a message to start chatting with lodrick-the-lafted/Densefin-291-Mistral-22B.
Model is too large to load in Inference API (serverless). To try the model, launch it on Inference Endpoints (dedicated) instead.