Yes, for most techniques you’d want to do
Quantization-aware training.
LLMS
-
Quantization-aware training recommended for most techniques
By
–
-

Free Course: Pretraining LLMs with Upstage and DeepLearning.AI
By
–



Explore "Pretraining LLMs," a short course developed with @upstageai. The course covers pretraining from scratch, continuing pretraining on custom data, and how using smaller open-source models can reduce costs. Take the course for free: hubs.la/Q02YFKyx0
-

Building Digital Workers: AI Agents Guide
By
–
Good over view of agents by Alfredo Sone "How to build digital workers" Touches on function calling, memory, multi agent systems, and more https://
medium.com/@alfredosone/a
i-agents-how-to-build-digital-workers-4fe68bb20348
… -

Orca AgentInstruct Dataset: Cleaned Data Generation Techniques
By
–
Don't sleep on the Orca AgentInstruct dataset Here's a cleaned and reformatted version: https://
huggingface.co/datasets/mlabo
nne/orca-agentinstruct-1M-v1-cleaned
… I also wrote an article about this new data generation family of techniques on @huggingface a few months ago: https://
huggingface.co/blog/mlabonne/
agentic-datagen
… -
Startup Community Innovation with Llama Derivatives
By
–
It's energizing to see the new derivatives and innovation from the startup community building with Llama!
-
Mistral Chat Now Free with FLUX Image Generation and Advanced Features
By
–
Le Chat now includes image generation with FLUX1.1, web search, canvas, mistral large with vision capabilities, PDF upload, etc.
And it's 100% free! https://
chat.mistral.ai -

20+ Essential AI Tutorials and Products from Abacus AI
By
–
Must see these 20+ #AI Tutorials: https://
blog.abacus.ai/blog/category/
ai-education/
… by @AbacusAI +
…plus check out all of the powerfully useful @AbacusAI products & services also!
————
#GenerativeAI #GenAI #AI #MachineLearning #ML #MLOps #DeepLearning #DataScience #DataScientists #LLMs #LLMOps #VectorDB -
JAMA Study: ChatGPT Diagnosis Performance by Inexperienced Doctors
By
–
Interesting ! However the @JAMA paper notes the doctors had “median years in practice = 3”. https://
nytimes.com/2024/11/17/hea
lth/chatgpt-ai-doctors-diagnosis.html?smid=nytcore-ios-share&referringSource=articleShare
… via @NYTimes -

Pixtral Large adds transformers support for AI models
By
–
Let's goo! @art_zucker aka – just added support for transformers https://
huggingface.co/mistralai/Pixt
ral-Large-Instruct-2411/discussions/3
… -

Siemens Energy Transforms Data into LLM-Ready Knowledge Base
By
–
Coming up: Attend our live webinar this Wednesday (11/20 ) to join Siemens Energy on their journey of transforming non-digitized data and technical documents into accessible insights, building a knowledge base ready to fine-tune LLMs. Join: https://
ow.ly/ijv850TXxnm