Great day for LLMs, @MistralAI just released Mistral & Pixtral Large – ~123B, 128K context, Multilingual, JSON + Function calling support & open weights! Pixtral Large:
> SoTA on MathVista, DocVQA, VQAv2
> Extends Mistral Large 2 123B multimodal decoder, 1B parameter vision
OPEN SOURCE
-
Mistral Releases Pixtral Large 123B Multimodal Model
By
–
-
New Pixtral-Large-Instruct version now available
By
–
BREAKING: Pixtral-Large-Instruct-2411 is now available on @huggingface. Evals to follow.
-
Drupal 11.1 introduces object-oriented hooks for modern PHP
By
–
Something to get excited about for @Drupal 11.1? Object-oriented hooks for more modern and performant @official_php
. Check out the module on Github to see this update in action! https://
bit.ly/4fMpMSv #drupal #drupal11 #drupaldevs -
Unsloth AI Training Code Works Across Cloud Local Environments
By
–
It's a good point. The training code uses @UnslothAI and can run pretty much anywhere: cloud GPUs, Colab notebooks, local machines, etc. I'll add a blob about that in the readme.
-
LLM Engineers Handbook: Training and Deployment Guide Updated
By
–
I just updated the official repo of the LLM Engineer's Handbook, already sitting at 1.6k I recommend checking out the LLMOps pipelines, especially if you're a researcher. Train and deploy with AWS, monitor with Opik, and run with ZenML. GitHub: https://
github.com/PacktPublishin
g/LLM-Engineers-Handbook
… -
PyTorch installation with conda and CUDA tools setup
By
–
I can’t recall having issues with it when using PyTorch. I still use conda (I just pop install PyTorch), so I could do ‘conda install cuda-nvcc-tools’ I guess
-
Open Source AI Breakthrough: Qwen 2.5 Coder and LLM2CLIP Released
By
–
What a brilliant week for Open Source AI! Qwen 2.5 Coder by @Alibaba_Qwen – 0.5B / 1.5B / 3B / 7B / 14B/ 32B (Base + Instruct) Code generation LLMs, with 32B tackling giants like Gemnini 1.5 Pro, Claude Sonnet LLM2CLIP from @MSFTResearch – Leverage LLMs to train ultra-powerful
-
Base Dataset Tag Feature Request for Dataset Management
By
–
I'd like to be able to have a "base_dataset" tag that works like "base_model". For example, this cleaned version https://
huggingface.co/datasets/mlabo
nne/orca-agentinstruct-1M-v1-cleaned
… should redirect to the original one. -
Essential Books for Building Strong Data Science Foundations
By
–
Books To Build Strong Foundations! #BigData #Analytics #DataScience #IoT #IIoT #PyTorch #Python #RStats #TensorFlow #Java #JavaScript #ReactJS #GoLang #CloudComputing #Serverless #DataScientist #Linux #Books #Programming #Coding #100DaysofCode https://
geni.us/Strong-Foundat
ion
… -
Open Source Biomolecular Model Matches AlphaFold3 Performance
By
–
that's a fully open source, commercially permissive biomolecular interaction model performing at the same level as AlphaFold3
— Vaibhav (VB) Srivastav (@reach_vb) 17 novembre 2024
open/ acc https://t.co/Rd16rIQFibthat's a fully open source, commercially permissive biomolecular interaction model performing at the same level as AlphaFold3 open/ acc