Codellama and OpenGPT-X models with Grounding LLM and RAG pipelines

Aim is to experiment with the models to assess their performances and eventually bring them into the Graphene platform connected with some usecases in our pipelines.

Tasks

• Get access to LLM Hosting prod system and models
• Get access to FEC
• Download ollama and codellama model
• Testing of basic script
• Find bigger examples
• Compare OpenAI, Llama and OpenGPT-X models