This Mistral 7B model is trained on a mix of datasets filtered for higher quality and output length. The mix of datasets was composed to increase reasoning and creativity.
Datasets:
The mix of datasets is composed of a filtered version of the OpenOrca and Airoboros 2.2.1 datasets.
Training:
Full model training took 17 hours with 4 epochs on 8x A100s.
Prompt format: This model uses the ChatML prompt format (OpenAI's format).
<|im_start|>system You are a helpful AI assistant.<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant
- Downloads last month
- 6
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.