We implemented pre-training in LitGPT (e.g., it was used to train TinyLlama back then): https://
github.com/Lightning-AI/l
itgpt/blob/main/litgpt/pretrain.py
…
I would strongly recommend looking at OLMo 2 otherwise: https://
github.com/allenai/OLMo/b
lob/main/olmo/train.py
…
TOOLS
-
LitGPT Pre-training Implementation and OLMo 2 Recommendation
By
–
-
Siemens for Startups: AI Tools at Reduced Cost
By
–
#Startups, this one’s for you! The @Siemens for Startups Program offers cutting-edge AI tools at a fraction of the cost. If you're building the future, don’t miss this opportunity! Learn more: https://
buff.ly/40GVXwP #sie_iiot #AI #TechInnovation @IIoT_World -
Mistral AI API pricing and performance comparison against OpenAI
By
–
2/ Crushing OpenAI on cost API pricing: $8 per million tokens (vs. OpenAI’s $30) Smaller models with similar performance Built for scalability—more AI for less money Image generation with Flux > Dall-E 3 – Free Mistral AI is proving that speed + efficiency =
-
Future ML with PyTorch project plans and timeline
By
–
The ML with PyTorch one? Agreed. I hope to get to it in the next 1-2 years!
-
GroqCloud Demos at LEAP 2025 Tech Arena with Field CTO
By
–
Stop by the Tech Arena at LEAP 2025 this week to chat with our Field CTO, Chris Stephens, and see demos of what GroqCloud™ can enable. Register at: https://
hubs.la/Q035Tbvg0 -
Windsurf Wave 2: AI for Developers
By
–
Loads of updates from Windsurf this month: Web search, memory, Deepseek R1 and o3-mini additions, plus much more 👀
— 🚨 AI News | TestingCatalog (@testingcatalog) 9 février 2025
"Windsurf wave 2: When AI actually gets how developers work" documented by @kernelkook on TestingCatalog 👇 https://t.co/ECOFP4EQVd pic.twitter.com/O41cxdtxjdLoads of updates from Windsurf this month: Web search, memory, Deepseek R1 and o3-mini additions, plus much more "Windsurf wave 2: When AI actually gets how developers work" documented by @kernelkook on TestingCatalog
-
Optimizing AI tool strengths and weaknesses for workplace effectiveness
By
–
I'm still looking for ways to optimize this for work. My goal at this stage is to learn its strengths and weaknesses and help inform others on its power.
-
All Top AI Models in One Subscription Deal
By
–
Get all the best models under a one subscription.
— Akshay 🚀 (@akshay_pachaar) 9 février 2025
This is the best deal you'll find.
• GPT 4o / o1-preview / o1-mini
• Claude Sonnet
• Gemini 2.0 Flash
• Grok
Also includes top open-source LLMs
• Llama 3.2
• Qwen 2.5
• DeepSeek
• DeepSeek-Fast
I have shared link to… pic.twitter.com/4o8xmoQj3bGet all the best models under a one subscription. This is the best deal you'll find. • GPT 4o / o1-preview / o1-mini
• Claude Sonnet
• Gemini 2.0 Flash
• Grok Also includes top open-source LLMs • Llama 3.2
• Qwen 2.5
• DeepSeek
• DeepSeek-Fast I have shared link to -
Pro Plan Deep Research Limitation Frustrates User Subscription
By
–
If I had known that I couldn't use 25 'Deep Research' per day, I wouldn't have subscribed to the Pro plan.
-
Exploring Cursor AI and Windsurf AI Development Tools
By
–
I started, but not thoroughly. I'm still on @cursor_ai and @windsurf_ai
, tbh! 🙂