On the code/framework aspect we’ve been working on it in @BigCodeProject and with StarCoder would be interesting to have your feedback for the next iteration of the project.
OPEN SOURCE
-
Training Data Transparency in Large Language Models Debate
By
–
Interesting. You think it’s better to hide the training data then? Currently in NLP the only chatbots widely deployed (and replacing search) are closed source so the situation is maybe a bit different. I’ll try to take some time write a blog post on this topic one day. It’s a
-
Credit vs Monetary Reward in Open Source Communities
By
–
I make a distinction between crediting & monetary reward. I know many people happy to share without monetary reward (the OSS community is all about that) but I know very few people who don't care at all about being credited (even anonymously) for something they've spent time on
-
Hugging Face Partnership Supports Next Generation AI Development
By
–
“We think it will take a village to raise the next generation of AI, and we see Hugging Face as a fantastic supporter of these same ideals.” Senior Dir. of Product Management Craig Wiley shared with @VentureBeat details on our new @huggingface feature
-
HuggingFace Launches Multi-Modal Agent API Chaining 100K Models
By
–
Excited to announce our multi-modal agent API that can automatically chain 100,000+ of HF models (stable diffusion, whisper, OpenAssistant,…) for text, audio, image, video, time-series,… based on your commands. All open-source so it can work locally! https://
huggingface.co/docs/transform
ers/transformers_agents
… -
Hugging Face Transformers Agents: Safe Code Execution Explained
By
–
"This code is then executed with our small Python interpreter on the set of inputs passed along with your tools. We hear you screaming 'Arbitrary code execution!' in the back, but let us explain why that is not the case." https://
huggingface.co/docs/transform
ers/transformers_agents
… -
Building and Deploying Custom Tools for AI Agents
By
–
Tools are elementary: a name, a description, a function. Designing a tool and pushing it to the Hub can be done in a few lines of code. The toolkit of the agent serves as a base: extend it with your tools, or with other community-contributed tools: https://
huggingface.co/docs/transform
ers/custom_tools
… -
Transformers Agents: Democratizing ML with Multimodal Control
By
–
We just released Transformers' boldest feature: Transformers Agents. This removes the barrier of entry to machine learning Control 100,000+ HF models by talking to Transformers and Diffusers Fully multimodal agent: text, images, video, audio, docs… https://
huggingface.co/docs/transform
ers/transformers_agents
… -
New experimental feature added to core library for community feedback
By
–
We think this is a really promising direction, so we're adding it to the core library But we also think there is a lot of work to do here, so we're adding it to the experimental module as we rapidly iterate In that vein, would love all thoughts/community contributions!