Glean for personal/self-hosted: is there an open source / self-hosted project that integrates pulling context from gmail, docs, sheets, calendar, whatsapp, ig, imessage, etc.?
OPEN SOURCE
-
Meta FAIR Releases Theory-of-Mind Research with Dataset and Code
By
–
New research from Meta FAIR — Meta Explore Theory-of-Mind: Program guided adversarial data generation for theory of mind reasoning. This work includes a new research paper, code & a dataset on @HuggingFace
. Details + eight more new releases from FAIR https://
go.fb.me/750ao2 -
Abacus AI LLM Fine-Tunes API Offers Affordable Open-Source Performance
By
–
Check out the @AbacusAI "LLM Fine-Tunes" inference API = Unlocks the power of affordable, Open-Source #LLMs — exceeds #GPT4o performance and is cheaper! Start here: https://
abacus.ai/llmapi
——
#LLMOps #AI #GenerativeAI #MachineLearning #MLOps #ML #GenAI #DeepLearning #DataScience -
Search and Learn: Lightweight LLM Search Toolkit with vLLM
By
–
Search and Learn: A lightweight toolkit for implementing search strategies with LLMs and built for speed with vLLM. You can check it out here.
-
DeepMind’s Compute-Optimal Scaling for Open Models
By
–
this blog cover: Compute-optimal scaling: How we implemented DeepMind’s recipe to boost the mathematical capabilities of open models at test-time. https://
huggingface.co/spaces/Hugging
FaceH4/blogpost-scaling-test-time-compute
… -
BiMediX2: Arabic-English Medical Vision Language Model
By
–
Fine-tuning Llama 3.1, researchers at @MBZUAI built BiMediX2, an Arabic-English VLM for medical use cases that excels in both text and visual tasks — including interpreting medical images from X-Rays, CT scans, MRIs and more https://
go.fb.me/amadbx -
Axelera AI Partners with Arduino for Edge AI Solutions
By
–
@AxeleraAI x @arduino = a game-changing partnership for AI at the Edge! Powerful #AI + open-source flexibility Catch the debut @ CES 2025 (Jan 7–10, Booth #60633, Vegas) Learn more: https://
axelera.ai/news/axelera-a
i-partners-with-arduino-to-bring-the-full-power-of-ai-to-the-edge
… More to come. A lot more!
#AI #EdgeComputing #CES2025 -
Falcon 3 Language Models Released: 1B to 10B Parameters
By
–
Falcon 3 is out! 1B, 3B, 7B, 10B (Base + Instruct) & 7B Mamba, trained on 14 Trillion tokens and apache 2.0 licensed! > 1B-Base surpasses SmolLM2-1.7B and matches gemma-2-2b
> 3B-Base outperforms larger models like Llama-3.1-8B and Minitron-4B-Base
> 7B-Base is on par with -
Meta’s Llama Leads Open-Source AI Production Solutions Race
By
–
The #AI race is shifting to production-ready solutions, & opensource innovation is leading the charge! @RodrigoLiang shares how @AIatMeta
's Llama is winning devs’ hearts & minds in @IBD_RKrause
's latest @IBDinvestors article. Discover it here https://
bit.ly/4ggV9Wc