New LLM plugin release: llm-anyscale-endpoints 0.5 adds support for their new hosted Mixtral 8x22B Instruct model, plus a "llm anyscale-endpoints refresh" command for refreshing the list of models without needing to upgrade the plugin in the future https://
github.com/simonw/llm-any
scale-endpoints/releases/tag/0.5
…
CODE
-
Anyscale Endpoints Plugin 0.5 Adds Mixtral 8x22B Support
By
–
-
PyTorch DDP Gradient Syncing Bug in Distributed Training
By
–
so last week I was posting about a bug i had with gradient syncing in torch DistributedDataParallel (DDP), aka the most standard way to do multi-GPU training for neural networks all of my misery originated with a single design decision from the torch team: DDP shares
-
One Size Doesn’t Fit All in Technology Solutions
By
–
I don't know what my requirements are yet – I build a lot of different things with a lot of different people, so the only thing I'm truly confident about is that one size is not going to fit all of them
-
Claude 3 Haiku Image-to-Haiku Demos and Tools
By
–
Here's the full list of demos. My favourite is probably that first one – Haikus from images with Claude 3 Haiku – which you can try out yourself here if you have a Claude 3 API key https://
tools.simonwillison.net/haiku -
Learning from Open Source AI Apps Feature Development
By
–
take @nutlope
’s notesgpt repo (or really any nontrivial oss ai app) and watch them add a feature -
Visualizing Computation DAGs: Identifying Narrow and Wide Bottlenecks
By
–
sorry i just made that word up in my head right now, didn't mean to hijack some existing term. I meant – imagine the computation as a DAG, lay it out in your head, and look for "narrow" and "wide" parts. Open to alternatives for future use!
-
SD3 Streamlit App for Simultaneous Image Generation
By
–
I wanted everyone to experience the magic of SD3, so I created this little Streamlit app that you can run on @Replit or via the repo. ✨
— Pietro Schirano (@skirano) 17 avril 2024
It generates an image using SD3 and SD3 Turbo simultaneously and supports image-to-image as well.
Just add your API key.
Have fun! 😌 pic.twitter.com/67kTCS7kxXI wanted everyone to experience the magic of SD3, so I created this little Streamlit app that you can run on @Replit or via the repo. It generates an image using SD3 and SD3 Turbo simultaneously and supports image-to-image as well. Just add your API key. Have fun!
-
SD3 Streamlit Implementation Repository Released
By
–
Github https://
github.com/Doriandarko/sd
3-streamlit
… -
C Language Overhead: Assembly Alternative Discussion
By
–
not C. too much overhead. try assembly instead
-
OpenAI Chunking Strategy: Assistants vs Custom Implementation
By
–
That's really useful, thanks My problem here is that if I don't know exactly how OpenAI chunking works I can't make a decision as to whether I should use the assistants mechanism or roll my own chunking strategy that's optimized for my particular use-case