正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

HRM-Text 101 is here. This tutorial takes you from zero to one: from setup to fine-tuning to evaluation. Download the base checkpoint. Fine-tune it on a real task. Evaluate the results. End to end, on a single GPU. Watch the tutorial and start building with HRM-Text.

Sapient Intelligence

5,412 subscribers

188,105 次观看 • 2 个月前 •via X (Twitter)

教育科学技术

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

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 次观看 • 27 天前

From AI imagination to GPU acceleration - this new tutorial shows how to build a full Astro Zombie Horde from a single image to final render.🧟‍♂️ Using AI tools on the front end and the The Render Network on the back, the entire pipeline comes together in hours - not days. Watch the full breakdown:

From AI imagination to GPU acceleration - this new tutorial shows how to build a full Astro Zombie Horde from a single image to final render.🧟‍♂️ Using AI tools on the front end and the The Render Network on the back, the entire pipeline comes together in hours - not days. Watch the full breakdown:

The Render Network

11,463 次观看 • 9 个月前

MolmoAct2 runs zero-shot on an SO-ARM101, no training required 🦾 Ai2 open Action Reasoning Model is now in LeRobot with the full lifecycle covered: fine-tuning (full or LoRA), evaluation, and real-robot deployment. It pairs a Molmo2-ER vision-language backbone with a flow-matching action expert to turn images, language, and proprioceptive state into action chunks. The best part: ready-made checkpoints ship with calibration correction baked in, so you can point it at your SO-100/101 and just watch it work. Inference fits in ~12GB at bf16, and LoRA fine-tuning runs on a single 24GB GPU. Big thanks to the Ai2 team for building this in the open.

MolmoAct2 runs zero-shot on an SO-ARM101, no training required 🦾 Ai2 open Action Reasoning Model is now in LeRobot with the full lifecycle covered: fine-tuning (full or LoRA), evaluation, and real-robot deployment. It pairs a Molmo2-ER vision-language backbone with a flow-matching action expert to turn images, language, and proprioceptive state into action chunks. The best part: ready-made checkpoints ship with calibration correction baked in, so you can point it at your SO-100/101 and just watch it work. Inference fits in ~12GB at bf16, and LoRA fine-tuning runs on a single 24GB GPU. Big thanks to the Ai2 team for building this in the open.

LeRobot

20,066 次观看 • 26 天前

Here is quick tutorial on the quickest way to repoduce/run NanoChat with minimal GPU setup time using Modal

Here is quick tutorial on the quickest way to repoduce/run NanoChat with minimal GPU setup time using Modal

Adithya S K

17,996 次观看 • 9 个月前

In this benchmark deep-dive, Sapient’s founders William and Guan are joined by research team members Changling and Yasin to unpack HRM-Text’s performance across MATH, DROP, ARC-Challenge, and MMLU. 📊 Beyond the scores, they discuss what each benchmark measures, how HRM-Text compares with larger models, and why efficiency matters. Watch the full discussion to learn more about HRM-Text and Sapient’s leaner path toward general intelligence.

In this benchmark deep-dive, Sapient’s founders William and Guan are joined by research team members Changling and Yasin to unpack HRM-Text’s performance across MATH, DROP, ARC-Challenge, and MMLU. 📊 Beyond the scores, they discuss what each benchmark measures, how HRM-Text compares with larger models, and why efficiency matters. Watch the full discussion to learn more about HRM-Text and Sapient’s leaner path toward general intelligence.

Sapient Intelligence

241,451 次观看 • 2 个月前

🎉 Meet Krea 2 from Krea, an aesthetic open-source image model ranked #1 text-to-image from an independent lab on Artificial Analysis. Day-0 support is now live in SGLang! Krea 2 ships as two models built to work together: 1️⃣ RAW: undistilled base checkpoint: diverse & malleable, made for fine-tuning, post-training & LoRA 2️⃣ Turbo: 8-step distilled checkpoint: fast, high-quality text-to-image Train LoRAs on RAW, run them on Turbo: base for training, Turbo for fast inference on your own hardware Run it now with SGLang!

🎉 Meet Krea 2 from Krea, an aesthetic open-source image model ranked #1 text-to-image from an independent lab on Artificial Analysis. Day-0 support is now live in SGLang! Krea 2 ships as two models built to work together: 1️⃣ RAW: undistilled base checkpoint: diverse & malleable, made for fine-tuning, post-training & LoRA 2️⃣ Turbo: 8-step distilled checkpoint: fast, high-quality text-to-image Train LoRAs on RAW, run them on Turbo: base for training, Turbo for fast inference on your own hardware Run it now with SGLang!

LMSYS Org

11,216 次观看 • 1 个月前

OpenAI engineer explained every form of fine-tuning in 1 hour 46 minutes - better than $3000 fine-tuning bootcamps. pick your task -> try prompting first -> drop to SFT for style -> run DPO for preference -> run RFT for verifiable rewards -> ship a model 10x cheaper than GPT-5. That loop is why teams that fine-tune beat teams that only prompt on cost and speed. Prompting + SFT + DPO + RFT + OpenAI fine-tuning API - that's the stack. Watch and save it, then pick the right fine-tune for your task this week.

OpenAI engineer explained every form of fine-tuning in 1 hour 46 minutes - better than $3000 fine-tuning bootcamps. pick your task -> try prompting first -> drop to SFT for style -> run DPO for preference -> run RFT for verifiable rewards -> ship a model 10x cheaper than GPT-5. That loop is why teams that fine-tune beat teams that only prompt on cost and speed. Prompting + SFT + DPO + RFT + OpenAI fine-tuning API - that's the stack. Watch and save it, then pick the right fine-tune for your task this week.

h100envy

40,941 次观看 • 20 天前

I just released a 2.5 hour long tutorial to show how to build a Mixed Reality game in Unity from start to finish. This is the most in depth tutorial I made on XR with: ✅Passthrough Setup ✅ Scene model ✅ Spawning objects ✅ Navmesh ✅ Publishing your game on the Meta Store!

I just released a 2.5 hour long tutorial to show how to build a Mixed Reality game in Unity from start to finish. This is the most in depth tutorial I made on XR with: ✅Passthrough Setup ✅ Scene model ✅ Spawning objects ✅ Navmesh ✅ Publishing your game on the Meta Store!

Quentin Valembois

12,694 次观看 • 1 年前

This is a distrubing sequence that flew under the radar on Sunday — clock running near end of Q3, less time on game clock than play clock, so taking it to the EOQ is fine. Texans clearly, though, wanna run a play. Fine. What’s NOT fine — (1) the play is VERY late getting called and (2) CJ and the offense seem to have zero clue the quarter is ending. Please tell me I’m off base here, I’d love to be wrong.

This is a distrubing sequence that flew under the radar on Sunday — clock running near end of Q3, less time on game clock than play clock, so taking it to the EOQ is fine. Texans clearly, though, wanna run a play. Fine. What’s NOT fine — (1) the play is VERY late getting called and (2) CJ and the offense seem to have zero clue the quarter is ending. Please tell me I’m off base here, I’d love to be wrong.

Sean Pendergast

1,791,501 次观看 • 10 个月前

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 次观看 • 20 天前

We just reached the text to mobile apps moment. CatDoes v3 lets you go from a single idea to a real iOS, Android and web app by chatting with AI agents. Here is a WhatsApp style app going from blank project to running on an iPhone in one session.

We just reached the text to mobile apps moment. CatDoes v3 lets you go from a single idea to a real iOS, Android and web app by chatting with AI agents. Here is a WhatsApp style app going from blank project to running on an iPhone in one session.

Chubby♨️

24,878 次观看 • 7 个月前

I recorded a video tutorial on building an AI Code Assistant. Going through the full stack - from data models to the front end. Using Postgres, pg_vector, LangChain, OpenAI, and NextJS.

I recorded a video tutorial on building an AI Code Assistant. Going through the full stack - from data models to the front end. Using Postgres, pg_vector, LangChain, OpenAI, and NextJS.

Gwen (Chen) Shapira

30,463 次观看 • 2 年前

LLM post-training used to mean fine-tuning to a downstream task Robotics has been stuck in this setting, needing task-specific fine-tuning for best performance π07 changes this: It works out of the box & outperforms fine-tuned specialists Details:

LLM post-training used to mean fine-tuning to a downstream task Robotics has been stuck in this setting, needing task-specific fine-tuning for best performance π07 changes this: It works out of the box & outperforms fine-tuned specialists Details:

Chelsea Finn

66,021 次观看 • 3 个月前

Apple built a large foundation model and fine-tuned it on multiple tasks. But they are doing something very clever: They load a single model in memory and use different adapters to specialize the model on the fly. I recorded a video to show you how to write the code to do the same thing Apple is doing. I explain everything step by step. Here is what I'll show you in the video: 1. We'll load two datasets 2. Then load a large model 3. Then, we'll fine-tune the model on both datasets I'll use LoRA to fine-tune the model. This process creates two small adapters, each specializing in solving one of the datasets. The base model's original parameters will remain unchanged. From here: 4. We'll generate a list of tasks 5. We'll load the correct adapter to solve each task The large model I'm using needs 346 MB of memory, but I only need to load it once. Each adapter is only 2.7 MB. I only need to load the base model once and pair it with any of the fine-tuned adapters. Minimum memory footprint and I can solve multiple tasks. Hope this helps!

Apple built a large foundation model and fine-tuned it on multiple tasks. But they are doing something very clever: They load a single model in memory and use different adapters to specialize the model on the fly. I recorded a video to show you how to write the code to do the same thing Apple is doing. I explain everything step by step. Here is what I'll show you in the video: 1. We'll load two datasets 2. Then load a large model 3. Then, we'll fine-tune the model on both datasets I'll use LoRA to fine-tune the model. This process creates two small adapters, each specializing in solving one of the datasets. The base model's original parameters will remain unchanged. From here: 4. We'll generate a list of tasks 5. We'll load the correct adapter to solve each task The large model I'm using needs 346 MB of memory, but I only need to load it once. Each adapter is only 2.7 MB. I only need to load the base model once and pair it with any of the fine-tuned adapters. Minimum memory footprint and I can solve multiple tasks. Hope this helps!

Santiago

84,747 次观看 • 1 年前

Introducing the EASIEST way to fine-tune Qwen 2 VL with a Hugging Face dataset! (Link to repo in first reply). You can either fine-tune inside or a Gradio app or with a single line of Python. Simply select your favorite image-text dataset and fine-tune! A special thanks to Faen Zhang and all those at HuggingFace and those behind Qwen 2 VL. blog coming soon!

Introducing the EASIEST way to fine-tune Qwen 2 VL with a Hugging Face dataset! (Link to repo in first reply). You can either fine-tune inside or a Gradio app or with a single line of Python. Simply select your favorite image-text dataset and fine-tune! A special thanks to Faen Zhang and all those at HuggingFace and those behind Qwen 2 VL. blog coming soon!

William J.B. Mattingly

21,466 次观看 • 1 年前

Here is a very powerful workflow combining Flux Kontext (from Black Forest Labs) and Kling 2.1 (from Kling AI ). Watch the super easy tutorial at the end and try it out on OpenArt today!

Here is a very powerful workflow combining Flux Kontext (from Black Forest Labs) and Kling 2.1 (from Kling AI ). Watch the super easy tutorial at the end and try it out on OpenArt today!

OpenArt

21,667 次观看 • 1 年前

You can now text an AI agent and it does the task inside the actual apps 🤯 It's called Airtap. No app to download. The conversation is the product. You can ask things like: - "Order an item from Amazon" - "See if Orangetheory has a 6am slot tomorrow" - "Post this photo to TikTok" Setup is one message. No download, no signup form. You can try Airtap Ai here:

You can now text an AI agent and it does the task inside the actual apps 🤯 It's called Airtap. No app to download. The conversation is the product. You can ask things like: - "Order an item from Amazon" - "See if Orangetheory has a 6am slot tomorrow" - "Post this photo to TikTok" Setup is one message. No download, no signup form. You can try Airtap Ai here:

Alvaro Cintas

99,458 次观看 • 22 天前

From a fresh install to teleoperating SO-101 robot arms in only 30 minutes. 🤖 Follow this step-by-step tutorial from Iulia Feroli to set up PyTorch, CUDA, ROS 2 Jazzy, and LeRobot on Jetson Orin with JetPack 7.2. Watch the full tutorial and follow along ➡️

From a fresh install to teleoperating SO-101 robot arms in only 30 minutes. 🤖 Follow this step-by-step tutorial from Iulia Feroli to set up PyTorch, CUDA, ROS 2 Jazzy, and LeRobot on Jetson Orin with JetPack 7.2. Watch the full tutorial and follow along ➡️

NVIDIA Robotics

32,704 次观看 • 14 天前

$Introducing HRM-Text. An ultra-lean 1B-parameter reasoning language model designed to deliver strong general performance with a fraction of the data, compute, and infrastructure. Trained on just 40B structured tokens, HRM-Text achieves competitive performance while using ~1/1000 of the training data of comparable models. The kicker? The full model trains in roughly one day on a $1,000 budget. This opens the door to a new generation of AI that is powerful, accessible, and radically easier to adapt. Theories and research concepts once deemed too expensive to test are officially back in the game. Sapient Intelligence invites you to help us shape a new paradigm for general intelligence.$

Introducing HRM-Text. An ultra-lean 1B-parameter reasoning language model designed to deliver strong general performance with a fraction of the data, compute, and infrastructure. Trained on just 40B structured tokens, HRM-Text achieves competitive performance while using ~1/1000 of the training data of comparable models. The kicker? The full model trains in roughly one day on a $1,000 budget. This opens the door to a new generation of AI that is powerful, accessible, and radically easier to adapt. Theories and research concepts once deemed too expensive to test are officially back in the game. Sapient Intelligence invites you to help us shape a new paradigm for general intelligence.

Sapient Intelligence

514,677 次观看 • 2 个月前