But for spaCy, we want to give people trained pipelines and have them be as applicable as possible across different domains. We also want people to be able to fine-tune the models on their data if it's not working ideally.
OPEN SOURCE
-
The Hashing Trick in spaCy Models: An Underexplored Technique
By
–
The hashing trick is an old technique from sparse linear models, well known in toolkits like Vowpal Wabbit. It's one of the unusual things I did in @spacy_io 's models that I've always felt was quite neat, and needed more experiments and write up.
-
Petals Creates Free Distributed Network for Running Text-Generating AI
By
–
Cool article from @Kyle_L_Wiggers @TechCrunch about Petals by @BigscienceW https://
techcrunch.com/2022/12/20/pet
als-is-creating-a-free-distributed-network-for-running-text-generating-ai
… -
Microsoft Data Science For Beginners Learning Resource
By
–
6) DS for begineers https://
github.com/microsoft/Data
-Science-For-Beginners
… -
BLOOM+1 Performance on Multilingual Prompting Benchmarks
By
–
I wonder how well BLOOM+1 would do on the multilingual prompting benchmarks proposed here:
-
nbdev writeup by Carson Dial appreciated
By
–
Many thanks to @carsondial for the writeup about nbdev 🙂
-
InfoWorld Names Best Open Source Software Winners 2022
By
–
Lots of great software amongst the @InfoWorld 2022 Best Open Source winners, including @huggingface Accelerate, @StableDiffusion
, Jax, @AiEleuther
, and our own #nbdev! https://
infoworld.com/article/367682
9/the-best-open-source-software-of-2022.html
… -
Reinforcement Learning Benchmark and Workshop with Open-Source Tools
By
–
Wonder what we're up to with reinforcement learning? We are excited to help enable this new benchmark and workshop, broadening how compute is re-used in RL with open-source tools and the Hub.
-
Should Hugging Face Expand Its Social Collaboration Features?
By
–
Should Hugging Face do more social features?