Using Mistral 7B v0.1 on Vultr

Quick Start

1. 1
   Create an account at Vultr and generate an API key.
2. 2
   Use the Vultr SDK or REST API to call mistral-7b — see the documentation for request format.

Code Examples

About Vultr

Vultr offers cloud GPU infrastructure with NVIDIA H100, A100, and AMD MI355X instances for AI workloads. The platform uses hourly billing and supports users deploying their own LLM inference workloads. Does not host pre-trained LLM models or provide managed LLM APIs.

Vultr is a cloud infrastructure company headquartered in West Palm Beach, Florida. The company provides infrastructure-as-a-service (IaaS) including bare metal servers, cloud servers, and GPU instances across a global network of 30+ data centers.

Pricing on Vultr

Capabilities

About Mistral 7B v0.1

Mistral 7B v0.1 is an advanced open-source large language model built by Mistral AI, consisting of 7 billion parameters. It's designed to deliver high performance and efficiency, outperforming many similar-sized models in various benchmarks. The model employs a transformer architecture with innovative features like Sliding Window Attention, Grouped-Query Attention, and a Byte-fallback BPE tokenizer, enhancing speed, reducing computational costs, and improving robustness. Capable of generating human-like text, following instructions effectively, and excelling in areas such as reasoning and mathematics, Mistral 7B v0.1 does have limitations, such as a lack of built-in moderation and a potential for hallucinations. Subsequent versions have sought to address these limitations while introducing extended context windows and improved instruction-following capabilities.