gm8xx8 pfp

gm8xx8

@gm8xx8

323 Following
818 Followers


gm8xx8 pfp
gm8xx8
@gm8xx8
nice collection 👀 Foundation Models for Vision https://huggingface.co/collections/merve/foundation-models-for-vision-6516d5c6af977f435be43ace
0 reply
0 recast
2 reactions

gm8xx8 pfp
gm8xx8
@gm8xx8
Open-sourcing in AI isn’t just generous, it’s smart strategy. It attracts top talent, speeds up development, and elevates the entire field. 💯 👏 https://x.com/clementdelangue/status/1707448869544440021?s=46
1 reply
0 recast
1 reaction

gm8xx8 pfp
gm8xx8
@gm8xx8
https://litellm.vercel.app/docs/embedding/supported_embedding
0 reply
0 recast
1 reaction

gm8xx8 pfp
gm8xx8
@gm8xx8
ChatGPT and GPT-4 excel in sorting and retrieving relevant information, often outperforming specialized methods. Even a small model trained on ChatGPT data can beat another trained on a much larger dataset. https://arxiv.org/abs/2304.09542
0 reply
0 recast
0 reaction

gm8xx8 pfp
gm8xx8
@gm8xx8
https://github.com/MaartenGr/KeyBERT
0 reply
0 recast
2 reactions

gm8xx8 pfp
gm8xx8
@gm8xx8
https://huggingface.co/blog/trl-ddpo
0 reply
0 recast
1 reaction

gm8xx8 pfp
gm8xx8
@gm8xx8
https://github.com/sapientml/sapientml
0 reply
0 recast
2 reactions

gm8xx8 pfp
gm8xx8
@gm8xx8
https://arxiv.org/abs/2309.16668
1 reply
1 recast
1 reaction

gm8xx8 pfp
gm8xx8
@gm8xx8
EvalLM, an interactive system designed for the nuanced evaluation of Large Language Model outputs, based on custom criteria and specific application needs. https://evallm.kixlab.org
0 reply
0 recast
2 reactions

gm8xx8 pfp
gm8xx8
@gm8xx8
https://medium.com/yeagerai/fine-tuning-or-rag-why-not-both-5c641fa750f8
0 reply
1 recast
3 reactions

gm8xx8 pfp
gm8xx8
@gm8xx8
AnyMAL: A unified model proficient in interpreting multiple data types like text, images, and sensors to generate text-based responses. Advanced, fine-tuned, and task-agnostic. https://arxiv.org/abs/2309.16058
0 reply
0 recast
1 reaction

gm8xx8 pfp
gm8xx8
@gm8xx8
Effective Long-Context Scaling of Foundation Models https://arxiv.org/abs/2309.16039
0 reply
0 recast
1 reaction

gm8xx8 pfp
gm8xx8
@gm8xx8
https://m.youtube.com/watch?feature=shared&v=cm7RWTcpSVA
0 reply
0 recast
2 reactions

gm8xx8 pfp
gm8xx8
@gm8xx8
https://marketplace.visualstudio.com/items?itemName=MartinOpenSky.whisper-assistant
0 reply
0 recast
0 reaction

gm8xx8 pfp
gm8xx8
@gm8xx8
Latest study spots flaws in Vision Transformer’s visual features. By simply adding more input tokens, the model’s efficiency boosts and yields cleaner, more effective image analysis. https://arxiv.org/abs/2309.16588
0 reply
0 recast
0 reaction

gm8xx8 pfp
gm8xx8
@gm8xx8
How Bryan Catanzaro jump-started Nvidia’s AI Big Bang https://www.fastcompany.com/90957372/how-bryan-catanzaro-jumpstarted-nvidias-ai-big-bang
0 reply
0 recast
2 reactions

gm8xx8 pfp
gm8xx8
@gm8xx8
New research develops a simple yet effective lie detector for large language models. By asking a set of follow-up questions, it can detect misinformation across different models and real world scenarios. Makes you wonder, is AI honesty within reach? 🤔 https://arxiv.org/abs/2309.15840
0 reply
0 recast
0 reaction

gm8xx8 pfp
gm8xx8
@gm8xx8
https://arxiv.org/abs/2309.16653
0 reply
0 recast
0 reaction

gm8xx8 pfp
gm8xx8
@gm8xx8
https://clarifai.com/mistralai/completion/models/mistral-7B-Instruct
0 reply
0 recast
1 reaction

gm8xx8 pfp
gm8xx8
@gm8xx8
Study reveals a streamlined technique for making LLMs produce problematic output, sidestepping existing safety protocols. The approach automates crafting risky queries, heightening concerns over the security of these AI systems. https://arxiv.org/abs/2307.15043
1 reply
1 recast
3 reactions