Raspberry Pi Pico (can access Wi-Fi) + GPT API w/ personality + voice input via Whisper and output via Coqui (and training data) + action figure = make your action figures your friends with a small ‘stick on’.
OPEN SOURCE
-
New BabyAGI Mod with Mini-Agent Tool for Search Results
By
–
I’m excited about this new @babyAGI_ mod I’m about to release. It has a “mini-agent” as a tool, in this case it: takes a search query scrapes each result page extracts relevant info by looping through chunks returns condensed results Fairly consistent
-
StarCoder Fine-tuned as Chat Assistant Using Community Datasets
By
–
So by popular demand, we've starting exploring the finetuning of BigCode's recently released code-completion model StarCoder (
https://
x.com/BigCodeProject
/status/1654174941976068119
…) to be a…. Chat Assistant We finetuned it on two high-quality datasets created by the community:
– OpenAssistant’s -
Stable Diffusion Competition Leaderboard Results Announced
By
–
We congratulate all participants for their amazing work, find the leaderboard and all the projects controlling Stable Diffusion here https://
huggingface.co/spaces/jax-dif
fusers-event/leaderboard
… -
JAX Diffusers Sprint Winners Showcase ControlNet Applications
By
–
Announcing the winners of JAX Diffusers sprint First place: https://
huggingface.co/spaces/control
net-interior-design/controlnet-seg
… Second place: https://
huggingface.co/spaces/ioclab/
brightness-controlnet
… Third Place: https://
huggingface.co/spaces/vllab/c
ontrolnet-hands
… -
LangChain Question Answering Instructions Tutorial
By
–
try these instructions? https://
python.langchain.com/en/latest/use_
cases/question_answering.html
… -
Hugging Face Hub experiences 12-hour outage affecting 250 users
By
–
POST-MORTEM @huggingface Through a combination of human error and technical issues, the Hub was experiencing some intermittent difficulties today for ~12 hours, and about 250 users and organizations were incorrectly displayed as deleted, which led to downtime for some great
-
ImageBind: Meta AI’s Multimodal Model Binding Six Data Types
By
–
Introducing ImageBind by Meta AI: the first AI model capable of binding data from six modalities at once. This breakthrough brings machines one step closer to the human ability to bind together information from many different senses.
— AI at Meta (@AIatMeta) 9 mai 2023
More on this new open source work ⬇️Introducing ImageBind by Meta AI: the first AI model capable of binding data from six modalities at once. This breakthrough brings machines one step closer to the human ability to bind together information from many different senses. More on this new open source work
-
RedPajamas and INCITE Models: New Open Source LLM Generation
By
–
And of course LLaMA isn't the only one. RedPajamas, from @togethercompute
, is based on the LLaMA training set and will likely breed a whole new generation of LLaMA-like OSS models—as well as its own RedPajama-INCITE 3B/7B models (keep an eye on that 3B one!!) -
Maximizing Power in Smaller AI Models for Local Deployment
By
–
The goal here is to squeeze as much power out of as small a model as possible. The smaller the model, the easier it is to update and tune—as well as run it cheaply (or even locally on a device).