With images and text, it seems perfectly reasonable to generate infinite variants till you’re happy. Code and video require too much manipulation of generations if you want changes and that requires skill.
CODE
-
Image generation versus code video control trade-offs
By
–
With images, the end users can obviously pull generations into photoshop and edit, but they tend to very often just generate *MORE* variations and just pick 1 Basically with code and video nobody wants to sacrifice control and it doesn’t make sense to generate infinite variation
-
Arpit Bhayani Live Codes Bloom Filters on Replit
By
–
Check out @arpit_bhayani live coding Bloom filters on Replit now! Here’s the Repl to follow along – https://
replit.com/@arpitbbhayani
/Bloom-Filter
… -
Spatial Transcriptomics Data Alignment Using Stalign
By
–
Aligning Spatial Transcriptomics Data With Stalign https://
bit.ly/3Iu1Mpb #AI #MachineLearning #DeepLearning #LLMs #DataScience -
LangChain Connects LLMs to Structured Data: Options Explored
By
–
Had a blast at @MindsDB conference yesterday – thanks @paxcema and and Jorge Talked a bit about how @langchain can help connect LLMs to your structured data and different options – embed it, query it, chains, agents, combinations Slides here:
-
TGI: Fast Production-Grade Open Source LLM Inference Library
By
–
If you find the Falcon too slow out-of-the-box in the transformers library, you should probably play with the super-fast production-grade OSS inference generation library TGI. Check it out here: https://
github.com/huggingface/te
xt-generation-inference
… -
TGI: Fastest Open Source LLM Inference Generation Server
By
–
you should use it in the fastest OSS inference generation server out there: TGI (
https://
github.com/huggingface/te
xt-generation-inference
…) Olivier the maintainer has been optimizing it with all his secret knowledge (well not so secret since it's an open-source repository hahaha) -
NVIDIA AI Agent Powered by GPT-4 Outperforms AutoGPT
By
–
Another article about our work https://t.co/MbeR69BbOO https://t.co/jKOkFCLG7n
— Prof. Anima Anandkumar (@AnimaAnandkumar) 2 juin 2023Another article about our work https://
gamingdeputy.com/nvidias-ai-age
nt-is-connected-to-gpt-4-outperforms-autogpt-and-writes-code-independently-to-dominate-my-world-without-human-intervention/
… -
Wuerstchen: Efficient Text-to-Image Model Pretraining Technique
By
–
Wuerstchen: Efficient Pretraining of Text-to-Image Models paper page: https://
huggingface.co/papers/2306.00
637
… introduce Wuerstchen, a novel technique for text-to-image synthesis that unites competitive performance with unprecedented cost-effectiveness and ease of training on constrained
