We’ve heard mixture-of-experts (MoE) were in the air (GPT4??) so we’ve just added the first one in the transformers library for you to play with 🙂 With for nothing less than a 1.3 trillion parameters checkpoint model on the hub! The largest model on the hub at the moment
OPEN SOURCE
-
Hugging Face Hub and Gradio Democratizing Machine Learning Ecosystem
By
–
Will be live in an hour to talk about @huggingface hub, Gradio and how the entire ecosystem comes together to democratise ML.
-
Galactica: Open-Source Large Language Model for Science
By
–
Paper: https://
galactica.org/static/paper.p
df
…
Github: https://
github.com/paperswithcode
/galai
…
Demo: https://
galactica.org -
Galactica: 120B Scientific Language Model for Research
By
–
"Galactica" is a large scientific language model with 120B parameters, that can be used for a lot of tasks including
⦿ Predicting citations
⦿ Generating literature review
⦿ Generating molecules ⦿ Generating Jupiter notebooks etc., -
Datasette tutorials organization in core repository
By
–
I started putting some tutorials together at https://
datasette.io/tutorials – but I've been wondering whether those should live in the core Datasette repository too -
Improving End-User Documentation for Data Projects
By
–
I've been puzzling over that myself! It's the big missing hole in my projects – most of them are developer-focused, so I can get away with mostly API documentation – but I'm very aware that @datasetteproj itself needs much better docs for end-users
-
Replit Terms: Training Data Access Rights Unclear
By
–
i got excited about this but then went through their terms. nothing in there says Replit has the right to access them for training data, though public Repls are MIT by default, many of these won't be public i'm guessing
-
Datasette Now Runs in WebAssembly Browser Environment
By
–
… update to this thread: I got Datasette working in WebAssembly! https://
lite.datasette.io and -
CR-SQLite WASM Implementation Now Available
By
–
Oh wow that thing's already working in WASM too? Exciting! https://
github.com/vlcn-io/cr-sql
ite/tree/main/pkg/wasm-esm/crsqlite
… -
Datasette Lite adds GitHub JSON loading capability
By
–
Added a new feature to http://
lite.datasette.io – it can now load JSON data directly from GitHub (or other CORS-friendly hosting) using the new ?json= URL parameter Documentation here: https://
github.com/simonw/dataset
te-lite#loading-json-data
…