We’ve made all #AlphaMissense predictions freely available to the research community through a catalogue, and a plugin created with our wonderful partners at @emblebi
OPEN SOURCE
-
Hugging Face Releases Open-Access Multimodal AI Model
By
–
Most people missed one of the most important news of the summer – open-access multi-modal (image + text) model coming out of @huggingface
! You can optimize it, fine-tune it and customize it for your use-case: https://
huggingface.co/blog/idefics You can try the fun version of it here: -
AI Helpers Transform Office Work Through Automation
By
–
Some startups and open source projects are building AI helpers that are remarkably skilled and flexible, and only occasionally go berserk. If they can iron out the problems, it might change office work forever.
-
Hilbert Space Gaussian Processes in PyMC Explained
By
–
PyMCon Web Series – Introduction to Hilbert Space GPs in PyMC – Bill Engels https://
bit.ly/3ExwMT1
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
Fine-tune LLMs 50x Faster with Ludwig and Ray
By
–
Headed to #RaySummit? Don't miss this lightning talk from Predibase CTO Travis Addair on how to #finetune #LLMs like LLaMa-2 50x faster with open-source Ludwig and Ray— in only 10 lines of YAML! https://
pbase.ai/3Rrp8AX -
NVIDIA partners with Anyscale to advance Ray LLM development
By
–
Today at #RaySummit, NVIDIA and @anyscalecompute announced they are partnering to bring NVIDIA AI to Ray open source and the Anyscale Platform, helping developers build, tune, train and scale production #LLMs. Learn more. https://
nvda.ws/3PG8blc -
Phi Models Outperform Larger Models: Open Textbook Initiative Needed
By
–
These new phi-1 & 1.5 models are fascinating, no? performances crushing 10 times bigger models secret sauce coming from a magic textbook dataset close to zero information on this dataset other than GPT3.5 generated Is it time for an "Open Textbook" project??
-
MAmmoTH: Open-Source LLMs for Mathematical Problem-Solving
By
–
10/ MAmmoTH – a series of open-source LLMs tailored for general math problem-solving; the models are trained on a curated instruction tuning dataset and outperform existing open-source models on several mathematical reasoning datasets.
-
Open-source library for building autonomous language agents
By
–
7/ Agents – an open-source library for building autonomous language agents including support for features like planning, memory, tool usage, multi-agent communication, and more.
