If I was starting a company today, I would look into productizing this model π https://t.co/3VyJXUDYDU
— Julien Chaumond (@julien_c) 25 octobre 2024
If I was starting a company today, I would look into productizing this model
By
–
If I was starting a company today, I would look into productizing this model π https://t.co/3VyJXUDYDU
— Julien Chaumond (@julien_c) 25 octobre 2024
If I was starting a company today, I would look into productizing this model
By
–
Yep i've seen this but I feel like it'd be cleaner to do a distinct file format for this (GGUF is very LLM centric, including metadata etc)
By
–
I kinda wish there was an equivalent to GGUF for Diffusers models DDUF?

By
–
I've said it before: Structured generation is the future The @dottxtai team has ported its core Outlines algos to rust, which means from now on, structured LLM generation is: – faster
– more robust
– embeddable into any ML software (no need for Python anymore) ^#3 is my
By
–
For Developer Experience: otherwise you have to explicitly list the parquet URLs in each query Alternatively there's support in @duckdb for hf:// patterns, BUT it's not supported in the WASM build just yet
By
–
must-read if you're interested in whatever's happening in AI in China
By
–
The guy in the middle looks AI for sure