@winglian wrangled deepspeed till it worked
@mattshumer_
-
Fine-tuned Mixtral 8x22B Inference Optimization Guide
By
–
Fine-tuned Mixtral 8x22B is ready. Curious what the easiest way to do inference is? Spinning up some GPUs for vLLM right now, is there something better?
-

Prompting Mixtral-8x22B: Effective Techniques Thread
By
–
Man I forgot how much more intensive prompting base models is All of this, just to shorten some text. Would anyone find value in a quick thread on how to prompt Mixtral-8x22B effectively?
-
JSONL Dataset Examples with Function Calling Implementation
By
–
That’s the craziest part. I literally copy + pasted 10 JSONL examples (with the JSONL!) from a dataset I had laying around. I made sure that about half of the examples showed some form of function calling.
-
Alpaca Format Model Getting Chat-Tuned Version Soon
By
–
Looks like Alpaca format 🙁 But I can tell you that a chat-tuned version will hit, for sure… the model is so good
-

Mixtral 8x22B Function Calling Now Officially Working
By
–
Officially have function calling working with base Mixtral 8x22B. This model is insanely powerful, especially with few-shot.
-
Mixtral 8x22B: Use Examples Instead of Instructions
By
–
FYI for anyone trying to get the most out of Mixtral 8x22B: don't try to prompt it like you prompt other models. It's a base model, not a tuned model. It isn't trained to follow instructions. Instead, provide examples of the behavior you're looking for. Far better results.
-
Build Any System: Community Ideas Challenge
By
–
Someone give me an idea for a system they want me to build, and I’ll record myself building it
-
Using AI to Write Code for AI Systems
By
–
Would anyone want me to post a video showing how I use AI to write code for AI systems? Poll isn’t working for some reason so let me know in the replies.
-

Custom Mixtral 8x22B Integrated into HyperWrite Platform
By
–
I've hacked a custom Mixtral 8x22B into the @HyperWriteAI platform. With access to real-time info. Will spend some time iterating and improving it, then we'll roll it out to our user base!