A fine-tuned version of the Mistral-7B model developed by Snorkel using PairRM for response ranking and Direct Preference Optimization (DPO) for model adaptation and refinement.
On-demand DeploymentDocs | On-demand deployments allow you to use Snorkel Mistral PairRM DPO on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits. |
