Gregory's ServerLooks like it's a big LLM release Monday today - so far Qwen 2.5 Turbo (API-only) and a new vision model from Mistral called Pixtral Large (open weights)
https://qwenlm.github.io/blog/qwen2.5-turbo/
https://mistral.ai/news/pixtral-large/
 4 comments
Notes on accessing Pixtral Large via LLM and llm-mistral on my blog: More notes on my blog: https://simonwillison.net/2024/Nov/18/pixtral-large/ @simon do you reckon this is a coincidence or is there coordination between different labs? @salvozappa I don't think there's any coordination in this case - I do sometimes suspect that OpenAI launch a big news feature deliberately on the same day as Gemini in order to undercut the press they get though! |
@simon I wonder what kind of hardware it takes to support a 1M token context window. That's amazing.