💭 About
I recently felt on this news:
Mistral AI makes its first large language model free for everyone | TechCrunchMistral AI makes its first large language model free for everyone | TechCrunch
Mistral, a French AI startup that raised a huge seed round in June, has debuted its first model, totally free to download and use.
techcrunch.com
The two key points that kept my attention were:
the model was released under the
Apache 2.0 license,...
and
Mistral 7Bis a further refinement of other “small” large language models likeLlama 2, offering similar capabilities (according to some standard benchmarks) at a considerably smaller compute cost
Then a few weeks later the release of the "GenAI Stack":
👉 So I started to look around... and find the benefits I could take out of these tools.
💭 Then & now
Actually my only two options were:
-
Use my OpenAI account and use
gpt-3.5-turboflavours orgpt-4to achieve custom projects (and share my data with OpenAI) - Use Kaggle GPUs resources & play with resources for free... still with the need to share (at least temporarly my resources) with Kaggle
🎯 What we'll achieve
With these two announcements, I wondered what I could achieve locally on my own hardware:
👉 This blog post is dedicated to the unboxing of this stack and the amazing perspectives it unleashes... and why Open Source matters.
🍿 Demo
💡 Load any custom model into ollama
Below a short an easy trick on how to install a finetuned custom model into ollama : jackalope-7b (a fine tuned version of Mistral-7B).
🔖 Bookmarks
More about GenAI stack
Top comments (13)