K-State Data Science @kstate_bigdata

Part of @kstate Center for #ArtificialIntelligence & #DataScience (#CAIDS) constellation. #BigData in #research, #science, #business, #courses, #academics kddresearch.org Manhattan, KS Joined April 2014

Tweets

11K
Followers

2K
Following

72
Likes

20K

Open Data Science @_odsc

3 days ago

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

2 1 3 544 0

Ray Fernando @RayFernando1337

2 weeks ago

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…

116 62 1K 223K 830

Download Image

Avi Chawla @_avichawla

3 weeks ago

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.

30 409 3K 248K 4K

Download Gif

Min Choi @minchoi

3 weeks ago

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

Min Choi @minchoi

3 weeks ago

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

185 154 2K 248K 854

Download Video

4 3 29 23K 11

Min Choi @minchoi

3 weeks ago

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…

4 11 95 19K 163

Min Choi @minchoi

3 weeks ago

Original Ani

1 6 83 9K 14

Download Video

Min Choi @minchoi

3 weeks ago

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 🤯

185 154 2K 248K 854

Download Video

Avi Chawla @_avichawla

4 weeks ago

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

Avi Chawla @_avichawla

4 weeks ago

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

43 225 3K 526K 5K

3 2 41 16K 44

Avi Chawla @_avichawla

4 weeks ago

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 👇

2 3 33 12K 32

Download Video

Avi Chawla @_avichawla

4 weeks ago

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 👇

1 2 21 11K 10

Download Image

Avi Chawla @_avichawla

4 weeks ago

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

2 2 18 12K 9

Download Image

Avi Chawla @_avichawla

4 weeks ago

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 👇

1 2 26 14K 10

Download Image

Avi Chawla @_avichawla

4 weeks ago

3️⃣ Load dataset We'll fine-tune gpt-oss and help it develop multi-lingual reasoning capabilities. So we load the multi-lingual thinking dataset, which has: - User query in English. - Reasoning in different languages. - Response in English. Check this 👇

1 2 29 17K 13

Download Image

Avi Chawla @_avichawla

4 weeks ago

2️⃣ Define LoRA config We'll use LoRA for efficient fine-tuning. To do this, we use Unsloth's PEFT and specify: - The model - LoRA low-rank (r) - Layers for fine-tuning, etc. Check this code 👇

1 3 34 20K 15

Download Image

Avi Chawla @_avichawla

4 weeks ago

1️⃣ Load the model We start by loading the gpt-oss (20B variant) model and its tokenizer using Unsloth. Check this 👇

1 4 41 22K 32

Download Image

Avi Chawla @_avichawla

4 weeks ago

Today, let's learn how to fine-tune OpenAI's latest gpt-oss locally. We'll give it multilingual reasoning capabilities as shown in the video. We'll use: - @UnslothAI for efficient fine-tuning. - @huggingface transformers to run it locally. Let's begin!

1 10 163 25K 242

Download Video

Avi Chawla @_avichawla

4 weeks ago

Let's fine-tune OpenAI gpt-oss (100% locally):

43 225 3K 526K 5K

Chris @chatgpt21

4 weeks ago

I’m actually really surprised GPT 5 thinking doesn’t hallucinate this. Most AI models will hallucinate a benchmark if they are very close to each other especially the difference between thinking and pro.