Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

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)

11,862 subscribers

40,189 views • 1 year ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

10 Comments

Eric Ciarla (hiring)1 year ago

See the open-source code, read the explainer article and get your Firecrawl API key here:

MightyBot1 year ago

🧠 Unified Search. Smarter Meetings. Effortless CRM. MightyBot is your AI agent platform for seamless workflows—record meetings, automate CRM updates, and find answers across apps in seconds. 🌟 Focus on what matters. We'll handle the grind.

Shadeform (YC S23)1 year ago

@deepseek_ai @firecrawl_dev This is great work!

Nicolas Camara1 year ago

@deepseek_ai @firecrawl_dev Very cool!

Neta Dror1 year ago

@firecrawl_dev @deepseek_ai I’m having an issue with the extract api… left you a message

Beshr1 year ago

@deepseek_ai @firecrawl_dev Any plans to enhance the web scraping APIs in firecrawl? I’d like the API to return less irrelevant elements and cleaner markdown, even if a bit slower/more-expensive.

Jesus Remon1 year ago

@deepseek_ai @firecrawl_dev This is awesome, will check to add it to to make better synthetic data

Victor M1 year ago

@deepseek_ai @firecrawl_dev Really cool! I really need to take some time to check out Firecrawl 🔥

NoBanks Nearby1 year ago

@deepseek_ai @firecrawl_dev Firecrawl is a very powerful tool ✊

Alberto Carmona1 year ago

@deepseek_ai @firecrawl_dev can you compare the pros and cons of having the model fine-tuned with the Firecrawl Doc and using the model as it is in a RAG solution with the same documentation?

Related Videos

🔥 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👇

🔥 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👇

Eric Ciarla (hiring)

28,794 views • 1 year ago

New short course on Fine-tuning LLMs! Many developers are moving beyond only prompting, to also fine-tuning LLMs - that is, taking a pre-trained model and training it further on your own data, which can deliver superior results inexpensively. In this course, Sharon Zhou, CEO of Lamini (disclosure: I’m a minor shareholder) shows you how to recognize when fine-tuning can be help, and how to train an open-source LLM on your own data. I hope you enjoy the course!

New short course on Fine-tuning LLMs! Many developers are moving beyond only prompting, to also fine-tuning LLMs - that is, taking a pre-trained model and training it further on your own data, which can deliver superior results inexpensively. In this course, Sharon Zhou, CEO of Lamini (disclosure: I’m a minor shareholder) shows you how to recognize when fine-tuning can be help, and how to train an open-source LLM on your own data. I hope you enjoy the course!

Andrew Ng

502,845 views • 2 years ago

introducing LoRAs for Krea 2 (beta). our most powerful fine-tuning system to date; now you can train Krea 2 on a your own specific style, object, or character with incredible precision. learn how it works 👇

introducing LoRAs for Krea 2 (beta). our most powerful fine-tuning system to date; now you can train Krea 2 on a your own specific style, object, or character with incredible precision. learn how it works 👇

Krea

42,464 views • 2 months ago

Today we're thrilled to announce the first end-to-end platform for Reinforcement Fine-Tuning. With just a dozen labeled data points, you can outperform #OpenAI o1 and #DeepSeekR1 on complex tasks. Built on the #GRPO methodology that DeepSeek-R1 popularized, our platform delivers exceptional results. In our real-world PyTorch to Triton transpilation case study, we achieved 3x higher accuracy than OpenAI o1 and DeepSeek-R1 when writing GPU code. Check out the thread below to learn how you can adapt an #opensource #LLM to your use cases with unmatched efficiency. #rft

Today we're thrilled to announce the first end-to-end platform for Reinforcement Fine-Tuning. With just a dozen labeled data points, you can outperform #OpenAI o1 and #DeepSeekR1 on complex tasks. Built on the #GRPO methodology that DeepSeek-R1 popularized, our platform delivers exceptional results. In our real-world PyTorch to Triton transpilation case study, we achieved 3x higher accuracy than OpenAI o1 and DeepSeek-R1 when writing GPU code. Check out the thread below to learn how you can adapt an #opensource #LLM to your use cases with unmatched efficiency. #rft

Predibase by Rubrik

1,022,448 views • 1 year ago

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

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 views • 1 year ago

🆕 How to run (and finetune) open source AI models with a simple API! In 5 mins, I go over how to: ◆ Generate text with DeepSeek R1 & Llama 3 ◆ Generate code with Qwen on LlamaCoder ◆ Generate images with Flux on BlinkShot ◆ Finetune a model on your own data & run it

🆕 How to run (and finetune) open source AI models with a simple API! In 5 mins, I go over how to: ◆ Generate text with DeepSeek R1 & Llama 3 ◆ Generate code with Qwen on LlamaCoder ◆ Generate images with Flux on BlinkShot ◆ Finetune a model on your own data & run it

Hassan

30,236 views • 1 year ago

Vibe marketing is here click on any element on your website to generate a variation that will convert better. data from the winners is used to fine-tune your own model. test -> learn -> keep winner -> repeat free until your CVR goes up 10%

Vibe marketing is here click on any element on your website to generate a variation that will convert better. data from the winners is used to fine-tune your own model. test -> learn -> keep winner -> repeat free until your CVR goes up 10%

Fab

739,244 views • 1 year ago

Well, even if you don’t care about your data going to China, I think it’s worth caring about not using a censored model that the DeepSeek app serves. And that’s why it’s worth using the R1 model on Perplexity with web search grounding and reasoning traces.

Well, even if you don’t care about your data going to China, I think it’s worth caring about not using a censored model that the DeepSeek app serves. And that’s why it’s worth using the R1 model on Perplexity with web search grounding and reasoning traces.

Aravind Srinivas

225,638 views • 1 year ago

OMG… you can now fine-tune your own AI model and run it entirely on your device. No servers. No API keys. No data leaks. Gemma 3 270M just made local LLMs real and it only takes about an hour to build your own. Here’s how:

OMG… you can now fine-tune your own AI model and run it entirely on your device. No servers. No API keys. No data leaks. Gemma 3 270M just made local LLMs real and it only takes about an hour to build your own. Here’s how:

Louis Gleeson

79,508 views • 9 months ago

You can now clone any website just by writing a prompt. Simply add the Firecrawl MCP server to your favorite AI coding tool for improved web data extraction, and let Claude code it for you. Here’s how:

You can now clone any website just by writing a prompt. Simply add the Firecrawl MCP server to your favorite AI coding tool for improved web data extraction, and let Claude code it for you. Here’s how:

Alvaro Cintas

83,031 views • 1 year ago

Meta's Joe Spisak explains how AI models can train themselves by generating images, asking itself questions about them, and choosing the best answers, in order to move beyond human data and human fine-tuning, and teach itself from synthetic data

Meta's Joe Spisak explains how AI models can train themselves by generating images, asking itself questions about them, and choosing the best answers, in order to move beyond human data and human fine-tuning, and teach itself from synthetic data

Tsarathustra

42,390 views • 1 year ago

Google engineer explained how to fine-tune a tiny LLM from 46% to 90% accuracy on your phone in 21 minutes - better than $1500 on-device AI bootcamps. pick Gemma 270M -> generate synthetic task data -> fine-tune with LoRA -> quantize to int4 -> deploy to Pixel and hit 2000 tokens per second. That loop is how a 270M model beats a 70B one on your task, running fully offline in your pocket. Gemma 270M + synthetic data + LoRA + int4 quantization + on-device runtime - that's the stack. Watch and save it, then fine-tune your own tiny agent tonight.

Google engineer explained how to fine-tune a tiny LLM from 46% to 90% accuracy on your phone in 21 minutes - better than $1500 on-device AI bootcamps. pick Gemma 270M -> generate synthetic task data -> fine-tune with LoRA -> quantize to int4 -> deploy to Pixel and hit 2000 tokens per second. That loop is how a 270M model beats a 70B one on your task, running fully offline in your pocket. Gemma 270M + synthetic data + LoRA + int4 quantization + on-device runtime - that's the stack. Watch and save it, then fine-tune your own tiny agent tonight.

h100envy

700,220 views • 20 days ago

You can now clone any website just by writing a prompt. Simply add the new Firecrawl MCP server to your favorite AI coding tool for improved web data extraction, and let Claude code it for you. Here’s how:

You can now clone any website just by writing a prompt. Simply add the new Firecrawl MCP server to your favorite AI coding tool for improved web data extraction, and let Claude code it for you. Here’s how:

Alvaro Cintas

539,649 views • 1 year ago

Many people are flat wrong about DeepSeek. You might think everyone freaked out about DeepSeek because the model is really good—which it is—or because it was from China, which is also true. But there's a more subtle reason: DeepSeek showed they could achieve those results using reinforcement learning instead of supervised fine-tuning. In other words, they didn't need an expensive phase where a bunch of people tuned the model by answering questions. They were able to do all of this faster and cheaper using reinforcement fine-tuning. This is a huge deal! I recorded the attached video with the following goals in mind: 1. Explain how reinforcement fine-tuning works 2. Show you how you can fine-tune your own models 3. Walk you through a complete code example

Many people are flat wrong about DeepSeek. You might think everyone freaked out about DeepSeek because the model is really good—which it is—or because it was from China, which is also true. But there's a more subtle reason: DeepSeek showed they could achieve those results using reinforcement learning instead of supervised fine-tuning. In other words, they didn't need an expensive phase where a bunch of people tuned the model by answering questions. They were able to do all of this faster and cheaper using reinforcement fine-tuning. This is a huge deal! I recorded the attached video with the following goals in mind: 1. Explain how reinforcement fine-tuning works 2. Show you how you can fine-tune your own models 3. Walk you through a complete code example

Santiago

105,589 views • 1 year ago

Learn to train an LLM with distributed data while ensuring privacy using federated learning in a new two-part short course, Intro to Federated Learning and Federated Fine-tuning of LLMs with Private Data, created with Flower and taught by Daniel J. Beutel and nic lane. Federated learning allows a single model to be trained across multiple devices, such as phones, or multiple organizations, such as hospitals, without the need to share data to a central server. This two-part course gives you an introduction to federated learning, and then teaches you how to fine-tune your large language model with distributed data using Flower Lab’s open source federated learning framework. You’ll learn: - How to use federated learning to train a variety of models, ranging from speech and vision models to LLMs, across distributed data while offering data privacy options to users and organizations. - Privacy Enhancing Technologies like differential privacy (DP), which obscures individual data by adding calibrated noise to query results. - Two variants of differential privacy - Central and Local - and how to choose depending on your use case. - How to measure and decrease bandwidth usage to make federated learning more practical and efficient with techniques like using pre-trained models and Parameter-Efficient Fine-Tuning - How federated LLM fine-tuning reduces the risk of leaking training data. Sign up here!

Learn to train an LLM with distributed data while ensuring privacy using federated learning in a new two-part short course, Intro to Federated Learning and Federated Fine-tuning of LLMs with Private Data, created with Flower and taught by Daniel J. Beutel and nic lane. Federated learning allows a single model to be trained across multiple devices, such as phones, or multiple organizations, such as hospitals, without the need to share data to a central server. This two-part course gives you an introduction to federated learning, and then teaches you how to fine-tune your large language model with distributed data using Flower Lab’s open source federated learning framework. You’ll learn: - How to use federated learning to train a variety of models, ranging from speech and vision models to LLMs, across distributed data while offering data privacy options to users and organizations. - Privacy Enhancing Technologies like differential privacy (DP), which obscures individual data by adding calibrated noise to query results. - Two variants of differential privacy - Central and Local - and how to choose depending on your use case. - How to measure and decrease bandwidth usage to make federated learning more practical and efficient with techniques like using pre-trained models and Parameter-Efficient Fine-Tuning - How federated LLM fine-tuning reduces the risk of leaking training data. Sign up here!

Andrew Ng

64,558 views • 2 years ago

With adjustable settings and a variety of presets, easily adjust your design to match your vision with the new Stylization Filter in #Substance3DPainter. Learn how to make the most of the filter, from using presets to fine-tuning custom settings:

With adjustable settings and a variety of presets, easily adjust your design to match your vision with the new Stylization Filter in #Substance3DPainter. Learn how to make the most of the filter, from using presets to fine-tuning custom settings:

Adobe Substance 3D

17,369 views • 1 year ago

New AI Package with DeepSeek AI Model TesseractAI continues to expand and improve our Custom AI Agent. You will now be able to add AI packages to your agent in addition to custom information. 🌟 This new feature is being developed using #DeepSeek AI model. In particular, DeepSeek R1 is designed for greater efficiency and more goal-oriented tasks, requiring fewer computational resources while still delivering powerful results. Additionally, we’re experimenting with DeepSeek’s technology for our existing Agent LLM to further enhance performance. Our goal is to make the Custom AI Agent even more efficient and effective for all your needs.

New AI Package with DeepSeek AI Model TesseractAI continues to expand and improve our Custom AI Agent. You will now be able to add AI packages to your agent in addition to custom information. 🌟 This new feature is being developed using #DeepSeek AI model. In particular, DeepSeek R1 is designed for greater efficiency and more goal-oriented tasks, requiring fewer computational resources while still delivering powerful results. Additionally, we’re experimenting with DeepSeek’s technology for our existing Agent LLM to further enhance performance. Our goal is to make the Custom AI Agent even more efficient and effective for all your needs.

Tesseract AI

13,236 views • 1 year ago

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.

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

492,166 views • 27 days ago

Remember reinforcement fine-tuning? We’ve been working away at it since last December, and it’s available today with OpenAI o4-mini! RFT uses chain-of-thought reasoning and task-specific grading to improve model performance—especially useful for complex domains. Take Accordance, which used RFT to fine-tune a model that’s SOTA for their tax and accounting purposes. And in supervised fine-tuning news: you can now fine-tune GPT-4.1 nano. Get even more from our fastest, cheapest model by training it specifically for your use-case.

Remember reinforcement fine-tuning? We’ve been working away at it since last December, and it’s available today with OpenAI o4-mini! RFT uses chain-of-thought reasoning and task-specific grading to improve model performance—especially useful for complex domains. Take Accordance, which used RFT to fine-tune a model that’s SOTA for their tax and accounting purposes. And in supervised fine-tuning news: you can now fine-tune GPT-4.1 nano. Get even more from our fastest, cheapest model by training it specifically for your use-case.

OpenAI Developers

663,794 views • 1 year ago