4️⃣ Prepare dataset Before fine-tuning, we must prepare the dataset in a conversational format: - We standardize the dataset. - We pick the messages field. - We apply the chat template to it. Check the code and a data sample 👇

5️⃣ Define Trainer Here, we create a Trainer object by specifying the training config, like learning rate, model, tokenizer, and more. Check this out 👇

6️⃣ Train With that done, we initiate training. The loss is generally decreasing with steps, which means the model is being fine-tuned correctly. Check this code and training logs 👇

Finally, the video shows prompting the LLM before and after fine-tuning. After fine-tuning, the model is able to generate the reasoning tokens in French before generating the final response in English. Check this 👇

That's a wrap! If you found it insightful, reshare it with your network. Find me → Avi Chawla Every day, I share tutorials and insights on DS, ML, LLMs, and RAGs.

This is wild. I just transformed Grok Companion Ani into a photorealistic actor and used Pika's new lipsync model for voice. This is 100% AI 🤯

Original Ani

Here is how I did it. Bookmark this for later: 1. Grab a profile image 2. Video containing audio of your choice (up to 60 secs) 3. Convert image using Flux Kontext with PROMPT: "Make this person real" 4. It's still in Early Testing, waitlist here apps.apple.com/us/app/pika-so…

If you enjoyed this thread, Follow me Min Choi and please Bookmark, Like, Comment & Repost the first Post below to share with your friends: x.com/minchoi/status…

A graph-powered all-in-one RAG system! RAG-Anything is a graph-driven, all-in-one multimodal document processing RAG system built on LightRAG. It supports all content modalities within a single integrated framework. 100% open-source.

Goodbye Claude Code... I hate to say this but Cursor + Claude 4 Sonnet Thinking (Max) 600k context is KING!!! Latest Cursor update is blazing FAST!! The intelligence for refactors, new feature implementations, and large context window leave large enough context windows for

NVIDIA CEO Jensen Huang projects a multi-trillion-dollar AI market by 2030, dismissing concerns of slowing demand despite a weaker sales forecast and trade uncertainty with China. #DataScience #AI #ArtificialIntelligence hubs.li/Q03GWZD00

The most important AI paper of 2025 might have just dropped. NVIDIA lays out a framework for Small Language Model agents that could outcompete LLMs. Here’s the full breakdown (and why it matters):

OpenAI and Microsoft have signed a non-binding memorandum of understanding (MOU) for the next phase of our partnership. We are actively working to finalize contractual terms in a definitive agreement. Together, we remain focused on delivering the best AI tools for everyone,

OpenAI started as a nonprofit, remains one today, and will continue to be one – with the nonprofit holding the authority that guides our future. As previously announced and as outlined in our non-binding MOU with Microsoft, the OpenAI nonprofit’s ongoing control would now be

OpenAI Newsroom This new structure seems designed to please one partner: Microsoft. But what about the 700M users who built your success? Keeping beloved models like 4o accessible isn't just nonprofit mission talk. It's about user retention, a metric your IPO investors (and Microsoft) will be

Announcing our public preview of Chrome DevTools MCP! Experience the full power of DevTools in your AI coding agent → goo.gle/4pDE6Tk With Chrome DevTools MCP, your AI agent can run performance traces, inspect the DOM, & perform real-time debugging of your web pages.

This is the real deal, holy moly

6️⃣0️⃣ 🥳 Help us celebrate the campus's 60th Anniversary with Willie the Wildcat at the Salina Selfie Station! There is no cost to attend! Read more about the special celebration event and our journey here: bit.ly/4oavp1l. #KStateSalina #BeWhatsNext

Time series data have the added complexity of temporal dependencies, seasonality, and possible non-stationarity. #teachthemachine f.mtr.cool/kzjgzkmtcc