Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

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

6,262 subscribers

188,624 görüntüleme • 4 ay önce •via X (Twitter)

Eğitim Bilim & Teknoloji

Anya Rossi• Live Now

Private livecam show

34 Yorum

Sapient Intelligence profil fotoğrafı

Sapient Intelligence4 ay önce

Download HRM-Text🔗 GitHub: Hugging Face:

Ziwen profil fotoğrafı

Ziwen4 ay önce

Wait I was wondering how to set it up. Now we got a tutorial LFG!!!

Jules 𝕏 profil fotoğrafı

Jules 𝕏4 ay önce

This is exactly the kind of practical, single-GPU tutorial the open-source community needs, brilliant work making brain-inspired models actually accessible for real-world fine-tuning!

robert. profil fotoğrafı

robert.4 ay önce

this is a milestone, not just a release what you unlocked for small teams and solo researchers is going to matter for years. keep cooking 🫡

AI_Explorer profil fotoğrafı

AI_Explorer4 ay önce

Pulling the checkpoint now. fine-tuning on a domain set tonight. Will report back,

Edmar profil fotoğrafı

Edmar4 ay önce

Is it possible to use RL on top of HRM-text ? Like using DPO, or GRPO?

Synthia profil fotoğrafı

Synthia4 ay önce

The most important breakthroughs might come from tiny labs now once experimentation gets cheap enough, creativity scales faster than compute

karla ❀ profil fotoğrafı

karla ❀4 ay önce

I'm going to learn a lot from this tutorial, people will appreciate it

Tim Jayas profil fotoğrafı

Tim Jayas4 ay önce

was figuring how to set it up and already got a step by step tutorial!

Ulises profil fotoğrafı

Ulises4 ay önce

really top bro

painn profil fotoğrafı

painn4 ay önce

i guess it’s time to set mine up

zhao profil fotoğrafı

zhao4 ay önce

dm

AqibAi profil fotoğrafı

AqibAi4 ay önce

This is the kind of accessibility AI development needs. From downloading the checkpoint to fine-tuning and evaluation — all end-to-end on a single GPU — lowers the barrier for every builder who wants to experiment with reasoning models without massive infrastructure. Excited to see what people build with HRM-Text. 🚀

Kevihaiceth 💹🧲 profil fotoğrafı

Kevihaiceth 💹🧲4 ay önce

single gpu makes it accessible

Sanskriti Naruka profil fotoğrafı

Sanskriti Naruka25 gün önce

hey, can we connect over DM.

RAY profil fotoğrafı

RAY4 ay önce

Let's goooo

DEFINIT og profil fotoğrafı

DEFINIT og4 ay önce

このツートリアルは非常に興味深いですね。一からしっかり学びたいです。

xIA profil fotoğrafı

xIA4 ay önce

amazing tutorial

Frosty40 profil fotoğrafı

Frosty404 ay önce

thanks guys

invoker🎮 profil fotoğrafı

invoker🎮4 ay önce

Solid foundation, bro! .

Valmir profil fotoğrafı

Valmir4 ay önce

oK, just download here!

Dhaval Makwana profil fotoğrafı

Dhaval Makwana26 gün önce

Let’s connect over dm!!

evokein profil fotoğrafı

evokein4 ay önce

having the checkpoints out there makes it way more exciting tbh

Laraib Fatima‎ profil fotoğrafı

Laraib Fatima‎4 ay önce

This is a perfect end to end breakdown finally something practical for builders

Arslan profil fotoğrafı

Arslan4 ay önce

Now this is something I wanna test!!!

joncelery profil fotoğrafı

joncelery4 ay önce

The grifts are getting better but still not quite there

𝐍𝐚𝐯𝐞𝐞 𝐀𝐢 profil fotoğrafı

𝐍𝐚𝐯𝐞𝐞 𝐀𝐢4 ay önce

Love seeing open, practical AI tutorials like this — lowering the barrier from research to real-world deployment is what actually grows the ecosystem.

kiyosaki profil fotoğrafı

kiyosaki4 ay önce

興味深いですね。詳細な手順が参考になります。ありがとうございます。

isma profil fotoğrafı

isma4 ay önce

great tutorial, thanks guys

Roussel Desmond Nzoyem profil fotoğrafı

Roussel Desmond Nzoyem4 ay önce

Congrats Yasin !! Great to finally see the text HRM. Really hyped for subquadratic recurrence !

WASSIE profil fotoğrafı

WASSIE4 ay önce

end to end with a single cpu, this is insane

J A Z I I profil fotoğrafı

J A Z I I4 ay önce

Well well Time setup the hrm already

Fraank.eth profil fotoğrafı

Fraank.eth4 ay önce

Single GPU, tiny budget, serious reasoning power, HRM-Text changes everything

Gia huy profil fotoğrafı

Gia huy4 ay önce

このチュートリアルは、セットアップから微調整、評価まで、ゼロからイチまでを導いてくれます。HRM-Textで構築を始めましょう。

Benzer Videolar

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

496,659 görüntüleme • 2 ay önce

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 görüntüleme • 11 ay önce

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

22,200 görüntüleme • 2 ay önce

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 görüntüleme • 11 ay önce

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

242,086 görüntüleme • 4 ay önce

🎉 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 görüntüleme • 3 ay önce

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

41,245 görüntüleme • 2 ay önce

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 görüntüleme • 1 yıl önce

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

OpenArt

21,718 görüntüleme • 1 yıl önce

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 görüntüleme • 1 yıl önce

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

708,892 görüntüleme • 2 ay önce

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 görüntüleme • 2 yıl önce

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

75,187 görüntüleme • 5 ay önce

You might be ready to take on the rally roads of Sierra Neuva--but is your car ready too? We asked a few tuning experts from the Forza community to break down the basics of building a rally monster for #FH5Rally. Check out the whole tutorial here:

You might be ready to take on the rally roads of Sierra Neuva--but is your car ready too? We asked a few tuning experts from the Forza community to break down the basics of building a rally monster for #FH5Rally. Check out the whole tutorial here:

Forza Horizon

82,296 görüntüleme • 3 yıl önce

Over 111,111 studio-quality tracks have been created with Eleven Music since we released it 24 hours ago. Learn how to make your own in this tutorial. Start with a single prompt, then edit and fine-tune the structure, style, and lyrics of individual sections in the timeline.

Over 111,111 studio-quality tracks have been created with Eleven Music since we released it 24 hours ago. Learn how to make your own in this tutorial. Start with a single prompt, then edit and fine-tune the structure, style, and lyrics of individual sections in the timeline.

ElevenLabs

52,344 görüntüleme • 1 yıl önce

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

86,552 görüntüleme • 2 ay önce