Evaluating Mistral Large and Custom LLMs
blog.trelis.com
Evaluating Mistral Large and Custom LLMs
Nicolas Carlini has released his benchmarking approach
New Video: Benchmarking GPT-4 vs Mistral Large (+ Much More)
➡️ How close is the new Mistral model to GPT-4?
➡️ How to evaluate performance on custom models?
Nicolas Carlini has released his benchmarking tool - based on about 100 tricky questions from his history of using GPTs.
It's a great guide for the quality of LLMs in coding applications.
That’s it for this week folks! Cheers, Ronan
Links:
➡️ Trelis Function-calling Models
➡️ One-click Fine-tuning & Inference Templates
➡️ Tip Jar