KerasCV now includes a Segment Anything implementation, which enables you to do image segmentation using only "prompt points". No training data needed. With the JAX backend, it runs ~5x faster on GPU than the original PyTorch implementation. Told you JAX was fast. Guide:
OPEN SOURCE
-
OpenAI Urged to Open-Source Technologies for Community
By
–
Any chance you could open-source these @OpenAI
? Would be an awesome service to the community! -
Groq MLAgility Performance Benchmarks and Argonne Workshop Recording
By
–
Open-source enthusiast curious about our perf results? Check out MLAgility where we show our performance on hundreds of off-the-shelf models compared to other vendors. Recording from our recent @argonne_lcf workshop for researchers using #inference to accelerate their work!
-
LangChain Community Growth Visualization Over Time
By
–
Our community is awesome!
— LangChain (@LangChain) 4 janvier 2024
Incredible to see this animation of the LangChain GitHub repository over time
Thank you to everyone who shows up!! Can you spot yourself? https://t.co/jTt7jGcdFjOur community is awesome! Incredible to see this animation of the LangChain GitHub repository over time Thank you to everyone who shows up!! Can you spot yourself?
-
Join AI Communities and Learn Machine Learning Together
By
–
I also put emphasis on joining communities and interacting with peers in machine learning for collective progress. Staying engaged is crucial for success as the field advances and to learn with others. All relevant links in the guide. Start learning AI: https://
github.com/louisfb01/star
t-machine-learning
… -
Integrating with Hugging Face Datasets Platform
By
–
Very cool! Would be nice to integrate with http://
hf.co/datasets cc @qlhoest -
Exploring Open Source Models Offline with Mixtral8x7b
By
–
https://
jan.ai Great way to try open source all models, like Mixtral8x7b offline. Love to see -
PyTorch Optimizes SDXL Pipeline by 3x Without C++
By
–
Check out our latest work on the PyTorch blog where we show how to optimize a default SDXL pipeline by 3x using pure PyTorch. No C++ code. Check out the blog post here https://
pytorch.org/blog/accelerat
ing-generative-ai-3/
… -
SOLAR-10.7B Model Enhanced with Direct Preference Optimization
By
–
#solarllm SOLAR-10.7B + Direct Preference Optimization (DPO)
-
Self-Extend LLM: Extending Context Window Without Fine-tuning
By
–
#solarllm #16K Very interesting work, Self-Extend LLM! "The proposed method does not require any training. With only four lines of code modification, it can effortlessly extend existing LLMs’ context window without any fine-tuning. We conducted comprehensive experiments, and the