like a crowdsourced dataset of LLM convos? could be cool to build with http://
hf.co/spaces + shared on http://
hf.co/datasets. We can amplify if you're building it
OPEN SOURCE
-
Crowdsourced LLM Conversations Dataset on Hugging Face
By
–
-
Nexusflow Releases Athene v2 72B Competitive Model
By
–
Nexusflow released Athene v2 72B – competetive with GPT4o & Llama 3.1 405B Chat, Code and Math > Arena Hard: GPT4o (84.9) vs Athene v2 (77.9) vs L3.1 405B (69.3) > Bigcode-Bench Hard: GPT4o (30.8) vs Athene v2 (31.4) vs L3.1 405B (26.4) > MATH: GPT4o (76.6) vs Athene v2
-
Community Contributions Drive Bug Fixes and Improvements
By
–
There are still lots of bugfixes and improvements contributed by community For more details, take a look at the release:
-
Ollama Multimodal: Image Processing and JSON Mode
By
–
2/7 Ollama multi modal Process images, files and enable JSON mode
-
Prometheus Grafana OpenTelemetry Native Support Flowise Monitoring
By
–
1/7 Prometheus Grafana, OpenTelemetry Native support for Prometheus with Grafana and OpenTelemetry for metrics such as API requests, counts of flows/predictions. https://
docs.flowiseai.com/using-flowise/
monitoring
… -
Flowise v2.1.4 Release: Prometheus, Ollama Multimodal, Cerebras LLM
By
–
Flowise v2.1.4 release Prometheus Grafana, OpenTelemetry Ollama multi modal Cerebras LLM Couchbase Vector Store Override Configuration
Postgres, MySQL support for Agent Memory Global Proxy : -
Cofunder advocates for smaller open AI models at Web Summit
By
–
So proud of my cofounder @Thom_Wolf, headlining the web summit to advocate for smaller & more open models for AI! pic.twitter.com/kCwBurJYUs
— clem 🤗 (@ClementDelangue) 14 novembre 2024So proud of my cofounder @Thom_Wolf
, headlining the web summit to advocate for smaller & more open models for AI! -
Groq and Meta Host Austin Llama Impact Hackathon Next Weekend
By
–
Join Groq & @AIatMeta next weekend for the Austin Llama Impact Hackathon. This unique opportunity will bring together the best developers across Austin's tech ecosystem to build new AI applications using Llama models.
-
Congratulations to François on Keras Legacy and New Journey
By
–
Congrats, François! Keras inspired thousands if not millions of people to begin their deep learning journey and through its design simplicity, it inspired the ecosystem of deep learning tools as whole. Wishing you the best in the new adventure!
-
SWE to MLE Transition: Enabling Engineers Career Paths
By
–
Congratulations on the legendary run! You’ve paved way for millions of SWEs transition to MLE and more. All the best for what’s next. Secretly hoping it’s Open Science/ Source too