the obvious next step from there is to recreate specific articles based on their eigentext vectors – essentially this part
LLMS
-
Eigenfaces for Text: PCA on Domain-Specific Embeddings
By
–
project request: eigenfaces, but for text do PCA on text embeddings from a particular domain and find the "eigentext" embeddings that represent that domain then project back to text with vec2text. what would the eigentexts look like? surprised no one has done this yet
-
LoRAX v0.8 Release: JSON Structured Outputs Support Added
By
–
New minor release for #LoRAX, our open-source framework for serving 100s of #LLMs on a single #GPU:
LoRAX v0.8 now supports structured outputs (#JSON mode) courtesy of #Outlines! -
TheProfessor V1: Abacus Introduces LLM Merging Technology
By
–
Introducing TheProfessor (V1) From Abacus, an LLM cocktail! We’ve recently talked about a fascinating property of LLMs, merging, where you can combine different layers from LLMs without needing pre-training. The merged LLM will then show combined properties of the different
-
Reka Flash AI Model Now Available on Poe Platform
By
–
You can try Reka Flash today at https://
poe.com/RekaFlash or via the Poe apps available on all platforms. -
Reka Flash 21B Multimodal Model Now Available on Poe
By
–
Reka Flash from @RekaAILabs is now available on Poe! Reka Flash is a state-of-the-art 21B multimodal language model that works with text, image, and short video input. Reka Flash is highly capable and very performant for its size. (1/2)
-
Video Breakdown Due to Excessive Token Count Limitation
By
–
The full video is well over 1 million tokens, which is why I broke it down. Just 30 minutes is already 500k tokens.
-
Create Deploy AI Agents with Abacus AI Tutorial
By
–
Create & deploy #AI agents with @AbacusAI at https://
abacus.ai/ai_agents — agents can chain user code, data transformations, models, & prompts. Boom! Learn how in this tutorial: https://
blog.abacus.ai/blog/2023/08/3
1/supercharge-productivity-accomplish-10x-more-with-ai-agents/
…
——
#DeepLearning #DataScience #MachineLearning #GenerativeAI #DataScientists #LLMs -
Gemma’s 256K Token Context: Analyzing Language Distribution Patterns
By
–
Keep in mind Gemma has a 256K tokens, so all text could be quite a bit shorter because there are so many merges. The interesting analysis here is to look at the *distribution* of token counts across different languages, and compare it to that same distribution for previous.
-
OlympiadBench: Challenging Benchmark Promoting AGI with Olympiad Problems
By
–
OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems He et al.: https://
arxiv.org/abs/2402.14008 #Artificialintelligence #DepLearning #MachineLearning