Mistral 7B v0.2
Readymodel path:accounts/fireworks/models/mistral-7b-v0p2
The Mistral-7B-v0.2 Large Language Model (LLM) is the successor to the Mistral-7B-v0.1 LLM featuring an increased context window for improved accuracy and performance. It was used to train the Mistral-7B-Instruct-v0.2 model
On-demand deployments allow you to use Mistral 7B v0.2 on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.