Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

🔥 We fine-tuned Gemma 3 using Unsloth AI on a custom instruction dataset scraped and built with . The model is now able to answer questions about OpenAI Agents SDK documentation. Check out the demo below👇

ericciarla's profile picture

Eric Ciarla (hiring)

15,851 subscribers

28,794 Aufrufe • vor 1 Jahr •via X (Twitter)

KunstWissenschaft & TechnologieBildung
LIVE

Anya Rossi• Live Now

Private livecam show

6 Kommentare

Profilbild von Eric Ciarla (hiring)
Eric Ciarla (hiring)vor 1 Jahr

See the breakdown of the fine-tuning process on our blog and get access to the full code here:

Profilbild von Etherspot 🐞
Etherspot 🐞vor 2 Jahren

Want to build a Web3 app without all the overhead costs? Try TransactionKit, a React toolkit that makes building dApps easy. Integrate cutting-edge account abstraction features in just a few clicks. Try it today 👇

Profilbild von Unsloth AI
Unsloth AIvor 1 Jahr

@firecrawl_dev @OpenAI Super cool guys! 🦥🔥

Profilbild von Mag Mario Jembrih
Mag Mario Jembrihvor 1 Jahr

@UnslothAI @firecrawl_dev @OpenAI Can you fine tune it similarly on local docs like pdfs or books in pdf up to 1k pages or wouldn’t you use it for that

Profilbild von Clyde
Clydevor 1 Jahr

@UnslothAI @firecrawl_dev @OpenAI Does that mean I can use it in cursor and it not wreck everything again?

Profilbild von Arsen Ibragimov
Arsen Ibragimovvor 1 Jahr

@UnslothAI @firecrawl_dev @OpenAI Check out the demo below.

Ähnliche Videos

Excited to introduce DeepSeek R1 fine-tuning with Firecrawl 🔥 Learn how to fine-tune DeepSeek's R1 model on custom instruction datasets generated by Firecrawl's web data extraction. Train your own AI expert to answer domain-specific questions about your website!
0:36

Excited to introduce DeepSeek R1 fine-tuning with Firecrawl 🔥 Learn how to fine-tune DeepSeek's R1 model on custom instruction datasets generated by Firecrawl's web data extraction. Train your own AI expert to answer domain-specific questions about your website!

Eric Ciarla (hiring)

40,189 Aufrufe • vor 1 Jahr

3️⃣ ways to run Gemma 3. Get a Gemma model up and running fast using Keras, Ollama, and the GenAI SDK in this demo from Developer Relations Engineer Marina Coelho.
6:30

3️⃣ ways to run Gemma 3. Get a Gemma model up and running fast using Keras, Ollama, and the GenAI SDK in this demo from Developer Relations Engineer Marina Coelho.

Google AI Developers

25,192 Aufrufe • vor 1 Jahr

Ex-NVIDIA engineer who built Unsloth explained RL, kernels, reasoning, quantization, and agents in 2 hours 42 minutes - better than $5000 fine-tuning bootcamps. pick the base model -> write triton kernels for 2x faster fine-tune -> quantize to 4-bit -> run GRPO/DPO -> ship a reasoning model on your single GPU. That loop is why Unsloth is the default way to fine-tune Llama, Qwen, Gemma, and Phi on hardware you already own. Unsloth + Triton kernels + 4-bit quantization + GRPO/DPO + single-GPU fine-tuning - that's the stack. Watch and save it, then fine-tune your first model tonight.
2:42:11

Ex-NVIDIA engineer who built Unsloth explained RL, kernels, reasoning, quantization, and agents in 2 hours 42 minutes - better than $5000 fine-tuning bootcamps. pick the base model -> write triton kernels for 2x faster fine-tune -> quantize to 4-bit -> run GRPO/DPO -> ship a reasoning model on your single GPU. That loop is why Unsloth is the default way to fine-tune Llama, Qwen, Gemma, and Phi on hardware you already own. Unsloth + Triton kernels + 4-bit quantization + GRPO/DPO + single-GPU fine-tuning - that's the stack. Watch and save it, then fine-tune your first model tonight.

h100envy

491,726 Aufrufe • vor 23 Tagen

OpenAI just released a new model to distinguish between AI/human written text to protect against ChatGPT. The classifier was trained on a pair of AI/human written dataset. However.. I was easily able to trick it by using GPT3 to rewrite the text. Demo:
0:32

OpenAI just released a new model to distinguish between AI/human written text to protect against ChatGPT. The classifier was trained on a pair of AI/human written dataset. However.. I was easily able to trick it by using GPT3 to rewrite the text. Demo:

Lior Alexander

195,429 Aufrufe • vor 3 Jahren

Introducing the GitHub Copilot SDK, now in technical preview 🆕 We’re opening up new ways to automate your workflows. Check out the SDK and the latest Copilot CLI features (including built-in custom agents and Homebrew/WinGet installation options). ▶️
1:21

Introducing the GitHub Copilot SDK, now in technical preview 🆕 We’re opening up new ways to automate your workflows. Check out the SDK and the latest Copilot CLI features (including built-in custom agents and Homebrew/WinGet installation options). ▶️

GitHub

27,029 Aufrufe • vor 6 Monaten

I built a Deep Research AI Agent team using OpenAI Agents SDK and Firecrawl. It combines multiple AI agents that can autonomously search the web, extract content, and generate detailed reports with enhanced analysis. 100% Opensource Code with step-by-step tutorials.
1:29

I built a Deep Research AI Agent team using OpenAI Agents SDK and Firecrawl. It combines multiple AI agents that can autonomously search the web, extract content, and generate detailed reports with enhanced analysis. 100% Opensource Code with step-by-step tutorials.

Shubham Saboo

50,831 Aufrufe • vor 1 Jahr

Introducing WebToAgent 🤖 Turn entire websites into AI assistants with 's LLMs.txt and OpenAI's Agents SDK Ask questions about any website with AI that actually understands the content. Try it yourself with the link below 👇
0:37

Introducing WebToAgent 🤖 Turn entire websites into AI assistants with 's LLMs.txt and OpenAI's Agents SDK Ask questions about any website with AI that actually understands the content. Try it yourself with the link below 👇

Eric Ciarla (hiring)

17,697 Aufrufe • vor 1 Jahr

🏆 Congrats to our NY Tech Week Hackathon Winners! 🥇 SEEYUH — @versatilitylab Built a zero-day vulnerability research system that uses the Agents SDK + o4-mini to orchestrate agent-based security analysis. (Demo below.) 🥈 Level Up — Adam Anzuoni & Kirk Kaiser Gamified employee onboarding with multimodal adventures powered by the Agents SDK, Realtime API, gpt-image-1, and o3. 🥉 Scotty — Faizan Created an AI interviewer for system design questions—interviewees respond via voice and sketch. Built with the Agents SDK + Realtime API.
2:10

🏆 Congrats to our NY Tech Week Hackathon Winners! 🥇 SEEYUH — @versatilitylab Built a zero-day vulnerability research system that uses the Agents SDK + o4-mini to orchestrate agent-based security analysis. (Demo below.) 🥈 Level Up — Adam Anzuoni & Kirk Kaiser Gamified employee onboarding with multimodal adventures powered by the Agents SDK, Realtime API, gpt-image-1, and o3. 🥉 Scotty — Faizan Created an AI interviewer for system design questions—interviewees respond via voice and sketch. Built with the Agents SDK + Realtime API.

OpenAI Developers

39,040 Aufrufe • vor 1 Jahr

IN: video fine-tuning support for AI at Meta's V-JEPA 2 in HF transformers 🔥 it comes with > fine-tuning notebook > four models fine-tuned on Diving48 and SSv2 dataset > FastRTC demo on V-JEPA2 SSv2 (see below) we're looking forward to see fine-tuned V-JEPA2 models on Hub ⏯️
0:36

IN: video fine-tuning support for AI at Meta's V-JEPA 2 in HF transformers 🔥 it comes with > fine-tuning notebook > four models fine-tuned on Diving48 and SSv2 dataset > FastRTC demo on V-JEPA2 SSv2 (see below) we're looking forward to see fine-tuned V-JEPA2 models on Hub ⏯️

merve

15,625 Aufrufe • vor 1 Jahr

Revolutionizing Move Programming with OpenLedger In this demo, we showcase how Move datasets contributed by data providers to OpenLedger’s datanets are used to fine-tune specialized models with LoRA fine-tuning. As seen in the video, we showcase an example on how builders can deploy a Move-specialized model that powers Co-pilot agents using our no-code model fine-tuning platform. This is the future of AI and Web3 innovation. Watch this space to see more specialised models and data feeds being built for next generation agents on top of OpenLedger #Move
3:58

Revolutionizing Move Programming with OpenLedger In this demo, we showcase how Move datasets contributed by data providers to OpenLedger’s datanets are used to fine-tune specialized models with LoRA fine-tuning. As seen in the video, we showcase an example on how builders can deploy a Move-specialized model that powers Co-pilot agents using our no-code model fine-tuning platform. This is the future of AI and Web3 innovation. Watch this space to see more specialised models and data feeds being built for next generation agents on top of OpenLedger #Move

OpenLedger

61,662 Aufrufe • vor 1 Jahr

Introducing the $COFFEE App & SDK - the versatile on-chain Agent infrastructure that allows anyone to build custom agents. Try it now: Any repo, language, framework, or plugin can now be added to agents. Build plugins, create agents, sell on our marketplace, and chat with Agents that can take on-chain actions. This is just the beginning. The foundation has been built. Together let’s integrate the powerful tools and plugins from the #Solana and #ETH ecosystems into the $COFFEE marketplace. We have some exciting plugins of popular agent repos we will be adding in the coming days and partnerships in the works. Stay tuned! ☕️ SDK and APIs to build custom, enterprise-grade agents:
2:07

Introducing the $COFFEE App & SDK - the versatile on-chain Agent infrastructure that allows anyone to build custom agents. Try it now: Any repo, language, framework, or plugin can now be added to agents. Build plugins, create agents, sell on our marketplace, and chat with Agents that can take on-chain actions. This is just the beginning. The foundation has been built. Together let’s integrate the powerful tools and plugins from the #Solana and #ETH ecosystems into the $COFFEE marketplace. We have some exciting plugins of popular agent repos we will be adding in the coming days and partnerships in the works. Stay tuned! ☕️ SDK and APIs to build custom, enterprise-grade agents:

Coffee - ai/acc ☕️

15,532 Aufrufe • vor 1 Jahr

Advice for AI engineers 💡 A small Visual Language Model fine-tuned on your custom dataset is as accurate as GPT-5... ... and costs 50 times less. For example, LFM2.5-VL-1.6B by Liquid AI running locally at full speed with llama.cpp ↓
0:24

Advice for AI engineers 💡 A small Visual Language Model fine-tuned on your custom dataset is as accurate as GPT-5... ... and costs 50 times less. For example, LFM2.5-VL-1.6B by Liquid AI running locally at full speed with llama.cpp ↓

Pau Labarta Bajo

80,190 Aufrufe • vor 5 Monaten

Introducing Based Agent: create AI agents with full onchain functionality on Base in less than 3 minutes. The era of Autonomous Onchain Agents is here Built with Coinbase Developer Platform🛡️ SDK, OpenAI , and Replit ⠕ oh, and you can make it an X bot too 😉
1:04

Introducing Based Agent: create AI agents with full onchain functionality on Base in less than 3 minutes. The era of Autonomous Onchain Agents is here Built with Coinbase Developer Platform🛡️ SDK, OpenAI , and Replit ⠕ oh, and you can make it an X bot too 😉

lincoln.base.eth

731,758 Aufrufe • vor 1 Jahr

It's finally possible: real-time in-browser speech recognition with OpenAI Whisper! 🤯 The model runs fully on-device using Transformers.js and ONNX Runtime Web, and supports multilingual transcription across 100 different languages! 🔥 Check out the demo (+ source code)! 👇
0:25

It's finally possible: real-time in-browser speech recognition with OpenAI Whisper! 🤯 The model runs fully on-device using Transformers.js and ONNX Runtime Web, and supports multilingual transcription across 100 different languages! 🔥 Check out the demo (+ source code)! 👇

Xenova

262,776 Aufrufe • vor 2 Jahren

Turn any website into AI art in under 30 seconds with Firecrawl + Imagen 4 🖼️ We built an open source app using @GoogleAIDevs new Gemini 2.5 Flash + Imagen models to turn scraped web content into fun generated visuals. Check out the tutorial video, blog, and repo below 👇
2:12

Turn any website into AI art in under 30 seconds with Firecrawl + Imagen 4 🖼️ We built an open source app using @GoogleAIDevs new Gemini 2.5 Flash + Imagen models to turn scraped web content into fun generated visuals. Check out the tutorial video, blog, and repo below 👇

Firecrawl

11,005 Aufrufe • vor 1 Jahr

Unsloth AI and NVIDIA are Revolutionizing Local LLM Fine-Tuning: From RTX Desktops to DGX Spark Fine-tune popular AI models faster with Unsloth on NVIDIA RTX AI PCs such as GeForce RTX desktops and laptops to RTX PRO workstations and the new DGX Spark to build personalized assistants for coding, creative work, and complex agentic workflows. The landscape of modern AI is shifting. We are moving away from a total reliance on massive, generalized cloud models and entering the era of local, agentic AI. Whether it is tuning a chatbot to handle hyper-specific product support or building a personal assistant that manages intricate schedules, the potential for generative AI on local hardware is boundless. However, developers face a persistent bottleneck: How do you get a Small Language Model (SLM) to punch above its weight class and respond with high accuracy for specialized tasks? The answer is Fine-Tuning, and the tool of choice is Unsloth. Unsloth provides an easy and high-speed method to customize models. Optimized for efficient, low-memory training on NVIDIA GPUs, Unsloth scales effortlessly from GeForce RTX desktops and laptop all the way to the DGX Spark, the world’s smallest AI supercomputer...... Full analysis: NVIDIA NVIDIA AI NVIDIA AIDev NVIDIAnewsroom Unsloth AI Unsloth
0:40

Unsloth AI and NVIDIA are Revolutionizing Local LLM Fine-Tuning: From RTX Desktops to DGX Spark Fine-tune popular AI models faster with Unsloth on NVIDIA RTX AI PCs such as GeForce RTX desktops and laptops to RTX PRO workstations and the new DGX Spark to build personalized assistants for coding, creative work, and complex agentic workflows. The landscape of modern AI is shifting. We are moving away from a total reliance on massive, generalized cloud models and entering the era of local, agentic AI. Whether it is tuning a chatbot to handle hyper-specific product support or building a personal assistant that manages intricate schedules, the potential for generative AI on local hardware is boundless. However, developers face a persistent bottleneck: How do you get a Small Language Model (SLM) to punch above its weight class and respond with high accuracy for specialized tasks? The answer is Fine-Tuning, and the tool of choice is Unsloth. Unsloth provides an easy and high-speed method to customize models. Optimized for efficient, low-memory training on NVIDIA GPUs, Unsloth scales effortlessly from GeForce RTX desktops and laptop all the way to the DGX Spark, the world’s smallest AI supercomputer...... Full analysis: NVIDIA NVIDIA AI NVIDIA AIDev NVIDIAnewsroom Unsloth AI Unsloth

Marktechpost AI Dev News ⚡

31,551 Aufrufe • vor 7 Monaten

🏆 Congrats to the winners of Viva Le Hack—our first hackathon in Paris (with a 6-hour build time!). 🥇 gitcontainer — cyclotruc Built a web app with the Agents SDK that turns any GitHub repo into a production-ready Dockerfile tailored to your project's tech stack. (Demo below.) 🥈 Hidden Gem — Benjamin Trom An AI-powered system that analyzes rooms, matches furniture, and creates realistic visualizations, using GPT-4.1, the Agents SDK, and Codex. 🥉 Nerd Radar — Josephine Parquet David Gelberg A lightweight research intelligence engine that helps you find, understand, and contact AI talent hidden in academic ecosystems. Built with Codex + OpenAI APIs.
0:28

🏆 Congrats to the winners of Viva Le Hack—our first hackathon in Paris (with a 6-hour build time!). 🥇 gitcontainer — cyclotruc Built a web app with the Agents SDK that turns any GitHub repo into a production-ready Dockerfile tailored to your project's tech stack. (Demo below.) 🥈 Hidden Gem — Benjamin Trom An AI-powered system that analyzes rooms, matches furniture, and creates realistic visualizations, using GPT-4.1, the Agents SDK, and Codex. 🥉 Nerd Radar — Josephine Parquet David Gelberg A lightweight research intelligence engine that helps you find, understand, and contact AI talent hidden in academic ecosystems. Built with Codex + OpenAI APIs.

OpenAI Developers

49,008 Aufrufe • vor 1 Jahr

.OpenAI GPT-5.5 is now available on Databricks, with Codex coding workflows and model inference fully governed through Unity AI Gateway. With GPT-5.5 on Databricks, you can: - Power coding workflows with Codex or other coding agents - Build custom agents grounded in enterprise data - Ask business questions in natural language from enterprise data with Genie - Automate document intelligence pipelines with Lakeflow Spark Declarative Pipelines Hear more from our co-founder, Patrick Wendell, and OpenAI CRO Denise Holland Dresser about how Databricks and OpenAI are bringing frontier AI to the enterprise. Get started today:
14:58

.OpenAI GPT-5.5 is now available on Databricks, with Codex coding workflows and model inference fully governed through Unity AI Gateway. With GPT-5.5 on Databricks, you can: - Power coding workflows with Codex or other coding agents - Build custom agents grounded in enterprise data - Ask business questions in natural language from enterprise data with Genie - Automate document intelligence pipelines with Lakeflow Spark Declarative Pipelines Hear more from our co-founder, Patrick Wendell, and OpenAI CRO Denise Holland Dresser about how Databricks and OpenAI are bringing frontier AI to the enterprise. Get started today:

Databricks

63,207 Aufrufe • vor 3 Monaten