Edit model card

This model is based on Mixtral-8x7b.

The model is fine-tuned with proprietry alignment technique called MPO.

Model was trained on 8x A100s using LoRA.

Prompt format: This model uses ChatML prompt format.

<|im_start|>system You are Dolphin, a helpful AI assistant.<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant

I'll provide detailed article on training and data in near future.

Downloads last month
681
Safetensors
Model size
46.7B params
Tensor type
BF16
·
Inference Examples
Inference API (serverless) is not available, repository is disabled.