Verta Integrations

The next generation of our open source large language model. This release includes model weights and starting code for pretrained and fine-tuned Llama language models — ranging from 7B to 70B parameters. Llama 2 pretrained models are trained on 2 trillion tokens, and have double the context length than Llama 1. Its fine-tuned models have been trained on over 1 million human annotations. Llama 2 outperforms other open source language models on many external benchmarks, including reasoning, coding, proficiency, and knowledge tests. Llama 2 was pretrained on publicly available online data sources. The fine-tuned model, Llama-2-chat, leverages publicly available instruction datasets and over 1 million human annotations. We have a broad range of supporters around the world who believe in our open approach to today’s AI — companies that have given early feedback and are excited to build with Llama 2.

We tackle the hardest problems to make AI models compute efficient, helpful and trustworthy. We spearhead the family of open models, we give to our users and empower them to contribute their ideas. Mistral-7B-v0.1 is a small, yet powerful model adaptable to many use-cases. Mistral 7B is better than Llama 2 13B on all benchmarks, has natural coding abilities, and 8k sequence length. It’s released under Apache 2.0 license, and we made it easy to deploy on any cloud.

Falcon is a blazing fast, minimalist Python web API framework for building robust app backends and microservices. The framework works great with both asyncio (ASGI) and gevent/meinheld (WSGI). The Falcon web framework encourages the REST architectural style. Resource classes implement HTTP method handlers that resolve requests and perform state transitions. Falcon complements more general Python web frameworks by providing extra reliability, flexibility, and performance wherever you need it. A number of Falcon add-ons, templates, and complementary packages are available for use in your projects. We've listed several of these on the Falcon wiki as a starting point, but you may also wish to search PyPI for additional resources.