I'm very excited about the synthetic data that can be created from chat logs. I can teach my LLMs in-context. They can create training data from this. Unfortunately, I run on a mac, and unsloth is linux only, but I imagine that a training loop will be included in all agents before too long. I imagine this happening at night while the LLM sleeps. ;)
![ค้าง (STILL) - GEMINI [ OFFICIAL MV ]](http://i.ytimg.com/vi/Ftxx3hk5vkU/mqdefault.jpg)
This channel is just so underrated, you videos are so informative and the way you explain it makes it so easy to understand, thank you so much!
Thanks for the support!
I'm very excited about the synthetic data that can be created from chat logs. I can teach my LLMs in-context. They can create training data from this. Unfortunately, I run on a mac, and unsloth is linux only, but I imagine that a training loop will be included in all agents before too long. I imagine this happening at night while the LLM sleeps. ;)
Great overview! 👍
Thanks! 👍
i have. an issue to install langchain in my env, upgraded my python too 3.11 but nothing change still the same problem :(
You're so energetic man !
i tried to do this and getting a "OutputParserException: This output parser can only be used with a chat generation" can anyone help
Can we achieve AGI with only LLMs?? 🎉🎉
🤔🤔🤔
How can we improve LLMs with fake data?
Training a model with the synthetic data it generate is like eating your own shit and expect it to be nutritional.