Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

After fixing a few bugs with inference code, I finally have a working pi0 set up! Fine-tuned overnight on single task data, it learns rough controls and no longer outputs unsafe actions. But mastering the task and form factor will require much more compute. Stay tuned!

VilleKuosmanen's profile picture

Ville🤖

2,645 subscribers

33,242 görüntüleme • 1 yıl önce •via X (Twitter)

Bilim & TeknolojiEğitim
LIVE

Anya Rossi• Live Now

Private livecam show

11 Yorum

Ville 🤖 profil fotoğrafı
Ville 🤖1 yıl önce

vibe checks - still struggling with instruction following like most VLAs. (Instruction comes from text, the speech is just for the demo and the robot won’t listen to that)

opensourceCM profil fotoğrafı
opensourceCM1 yıl önce

What’s the cost of mistakes in your contracts? If you work with contracts day-to-day, it’s time to automate. Track every detail, streamline workflows ... ✨ Make managing contracts as easy as a few clicks. Visit our new website & book your demo today!

Stone Tao profil fotoğrafı
Stone Tao1 yıl önce

success rate / how many fine tuning demos?

Ville 🤖 profil fotoğrafı
Ville 🤖1 yıl önce

0% I need to fine-tune much longer to do justice for this model 😅

Vaishak V Kumar profil fotoğrafı
Vaishak V Kumar1 yıl önce

What changed?

Ville 🤖 profil fotoğrafı
Ville 🤖1 yıl önce

fixed several bugs with the infra and re-trained the model - not 100% sure what parts mattered and what didn't robotics is hard

David Bar profil fotoğrafı
David Bar1 yıl önce

Cool

SuperMario profil fotoğrafı
SuperMario1 yıl önce

Great work!

Eugene Mironov profil fotoğrafı
Eugene Mironov1 yıl önce

Looks cool, looking forward to try it too

Ville 🤖 profil fotoğrafı
Ville 🤖1 yıl önce

I'm looking forward to trying your RL code once ready!

Pierre-Louis Biojout profil fotoğrafı
Pierre-Louis Biojout1 yıl önce

How much episodes in your dataset? Given the size of the model, without some little tricks you need a decent amount of datapoints

Benzer Videolar

Please retweet this and spread the word! After many hard weeks of finishing and working, we finally have ✨Vs Kyu 1.1✨! It fixed a lot of things and added a few more elements! Stay tuned! FNF News Funkin News CommunityGame
0:29

Please retweet this and spread the word! After many hard weeks of finishing and working, we finally have ✨Vs Kyu 1.1✨! It fixed a lot of things and added a few more elements! Stay tuned! FNF News Funkin News CommunityGame

Kyu

149,720 görüntüleme • 3 yıl önce

QVAC SDK will support in 0.9.0 (gonna be release in ~10 days) LoRA fine-tuning directly on-device, letting developers customize LLMs with their own data without sending anything to the cloud. You just load a base model, point it at your training dataset, and get a lightweight LoRA adapter back — all running locally. The fine-tuned model can then be used for inference immediately, with no extra setup. Why it matters: LoRA (Low-Rank Adaptation) fine-tuning lets you specialize a general-purpose language model for your specific use case — like matching a brand's tone, mastering domain terminology, or following a particular output format — using a fraction of the compute a full fine-tune would require. QVAC handles the entire workflow locally: dataset preparation, training with configurable hyperparameters, checkpoint saving, and seamless inference with the resulting adapter. Your data never leaves the device. The developer experience: Fine-tuning with QVAC is as simple as calling "sdk.finetune()" with your dataset and a few hyperparameters. Training runs entirely on your local hardware, produces a compact LoRA adapter file, and supports pause/resume so you can stop a job and pick it back up without losing progress. The result plugs straight into QVAC's inference pipeline — no model conversion, no deployment step, just immediate local completions with your fine-tuned model.
0:33

QVAC SDK will support in 0.9.0 (gonna be release in ~10 days) LoRA fine-tuning directly on-device, letting developers customize LLMs with their own data without sending anything to the cloud. You just load a base model, point it at your training dataset, and get a lightweight LoRA adapter back — all running locally. The fine-tuned model can then be used for inference immediately, with no extra setup. Why it matters: LoRA (Low-Rank Adaptation) fine-tuning lets you specialize a general-purpose language model for your specific use case — like matching a brand's tone, mastering domain terminology, or following a particular output format — using a fraction of the compute a full fine-tune would require. QVAC handles the entire workflow locally: dataset preparation, training with configurable hyperparameters, checkpoint saving, and seamless inference with the resulting adapter. Your data never leaves the device. The developer experience: Fine-tuning with QVAC is as simple as calling "sdk.finetune()" with your dataset and a few hyperparameters. Training runs entirely on your local hardware, produces a compact LoRA adapter file, and supports pause/resume so you can stop a job and pick it back up without losing progress. The result plugs straight into QVAC's inference pipeline — no model conversion, no deployment step, just immediate local completions with your fine-tuned model.

Paolo Ardoino 🤖

42,271 görüntüleme • 2 ay önce

Ogechi Remix video been out a few days go keep running it up! And stay tuned for many more announcements on the horizon 👀
0:48

Ogechi Remix video been out a few days go keep running it up! And stay tuned for many more announcements on the horizon 👀

Davido

479,207 görüntüleme • 1 yıl önce

train YOLOv9 on your dataset tutorial - run inference with a pre-trained COCO model - fine-tune model on custom dataset - evaluate the trained model - run inference with a fine-tuned model blogpost: ↓ read more
0:30

train YOLOv9 on your dataset tutorial - run inference with a pre-trained COCO model - fine-tune model on custom dataset - evaluate the trained model - run inference with a fine-tuned model blogpost: ↓ read more

SkalskiP

111,792 görüntüleme • 2 yıl önce

OpenLora is the designated deployment engine for specialized models in the OpenLedger ecosystem. By leveraging just-in-time adapter switching, OpenLora enables the efficient serving of thousands of fine-tuned LoRA adapters on a single GPU, drastically reducing deployment costs. Unlike generic models, OpenLora-powered specialized models require fewer input tokens and produce more optimized, precise outputs - minimizing both input and output token size while delivering task-specific performance at scale. Faster, Smarter, and Specialized.
2:24

OpenLora is the designated deployment engine for specialized models in the OpenLedger ecosystem. By leveraging just-in-time adapter switching, OpenLora enables the efficient serving of thousands of fine-tuned LoRA adapters on a single GPU, drastically reducing deployment costs. Unlike generic models, OpenLora-powered specialized models require fewer input tokens and produce more optimized, precise outputs - minimizing both input and output token size while delivering task-specific performance at scale. Faster, Smarter, and Specialized.

OpenLedger

76,393 görüntüleme • 1 yıl önce

What a day on set with 1xBet México ! 🎥⚽️ Always a pleasure working with a top team and bringing the best to you! 💪🏼💙 Stay tuned for more surprises coming soon! 🚀 #1XBET
1:02

What a day on set with 1xBet México ! 🎥⚽️ Always a pleasure working with a top team and bringing the best to you! 💪🏼💙 Stay tuned for more surprises coming soon! 🚀 #1XBET

Guillermo Ochoa

15,309 görüntüleme • 1 yıl önce

#SonicBattleRush is ramping up the gameplay once more! We have a lot of exciting stuff in the working. Stay tuned for more!
0:21

#SonicBattleRush is ramping up the gameplay once more! We have a lot of exciting stuff in the working. Stay tuned for more!

Sonic Battle Rush

77,413 görüntüleme • 1 yıl önce

The problem with humanoid teleoperation is that it is expensive and difficult to scale Enter NVIDIA's EgoScale: - A VLA model pretrained on thousands hours of egocentric human videos. - Mid-trained via 50 hours of human + 4 hours of robot "play" data for human-robot alignment. - Fine-tuned with very few examples of task-specific robot teleoperation (100 or fewer per task). - Successfully transfers across 5-finger (Sharpa) and 3-finger (Unitree G1) robot hands. - Performance scales predictably as data increases.
0:50

The problem with humanoid teleoperation is that it is expensive and difficult to scale Enter NVIDIA's EgoScale: - A VLA model pretrained on thousands hours of egocentric human videos. - Mid-trained via 50 hours of human + 4 hours of robot "play" data for human-robot alignment. - Fine-tuned with very few examples of task-specific robot teleoperation (100 or fewer per task). - Successfully transfers across 5-finger (Sharpa) and 3-finger (Unitree G1) robot hands. - Performance scales predictably as data increases.

The Humanoid Hub

44,441 görüntüleme • 3 ay önce

Feels like summer but it’s still Spring! Finally after a long cool spring we have a few fine warm days, soak it up and enjoy it but remember the sunscreen.
0:43

Feels like summer but it’s still Spring! Finally after a long cool spring we have a few fine warm days, soak it up and enjoy it but remember the sunscreen.

Carlow Weather

26,413 görüntüleme • 22 gün 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:
1:14

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

60,007 görüntüleme • 2 ay önce

GM FAM! 🌅 Follow us on this journey so much more coming… stay tuned and have a good one! 🫡💙
0:20

GM FAM! 🌅 Follow us on this journey so much more coming… stay tuned and have a good one! 🫡💙

ivault™

226,730 görüntüleme • 25 gün önce

Working on a guide for anyone looking to partake in The Hildi's film festival but have no idea where to start! Stay tuned.
0:26

Working on a guide for anyone looking to partake in The Hildi's film festival but have no idea where to start! Stay tuned.

Aethermancer Studios

11,089 görüntüleme • 4 ay önce

PART 5 IS FINALLY HERE It took a while but after all time i think it turned out fine, hope you like it too and stay tuned for part 6 #tadc #TADC #TADCEp7 #tadcpomni #tadcart #TADCribbit #tadcjax #jax #pomni #funnybunny #animation
1:02

PART 5 IS FINALLY HERE It took a while but after all time i think it turned out fine, hope you like it too and stay tuned for part 6 #tadc #TADC #TADCEp7 #tadcpomni #tadcart #TADCribbit #tadcjax #jax #pomni #funnybunny #animation

Chaluke

22,576 görüntüleme • 6 ay önce

Short update on the T Unit progress as some people have been waiting. Basically, most if not all the graphics are complete, however, there are some palette corruption bugs, not sure what it is about, but will take a look. There's some flickering, maybe due to performance related issues, but will investigate. Sound partially working on the ADPCM, still have a bit to do on the DCS sound board though, been working for a few months on it, it is pretty large. Stay Tuned! #CoinOpCollection #Midway
1:34

Short update on the T Unit progress as some people have been waiting. Basically, most if not all the graphics are complete, however, there are some palette corruption bugs, not sure what it is about, but will take a look. There's some flickering, maybe due to performance related issues, but will investigate. Sound partially working on the ADPCM, still have a bit to do on the DCS sound board though, been working for a few months on it, it is pretty large. Stay Tuned! #CoinOpCollection #Midway

Pramod Somashekar

18,042 görüntüleme • 3 ay önce

NVIDIA has published a paper on DREAMGEN – a powerful 4-step pipeline for generating synthetic data for humanoids that enables task and environment generalization. - Step 1: Fine-tune a video generation model using a small number of human teleoperation videos - Step 2: Prompt the fine-tuned model to turn a single real image into new AI-imagined videos - Step 3: Automatically label actions in the generated videos - Step 4: Train a robot AI model with the labeled synthetic dataset This enabled humanoid robots to perform 22 novel behaviors – such as pouring, opening/closing articulated objects, and manipulating a variety of tools. The original teleoperation dataset only included pick-and-place tasks. This takes task extensibility to another level without requiring human teleoperation for every single task. The pipeline will be made open-source soon. Project page:
0:37

NVIDIA has published a paper on DREAMGEN – a powerful 4-step pipeline for generating synthetic data for humanoids that enables task and environment generalization. - Step 1: Fine-tune a video generation model using a small number of human teleoperation videos - Step 2: Prompt the fine-tuned model to turn a single real image into new AI-imagined videos - Step 3: Automatically label actions in the generated videos - Step 4: Train a robot AI model with the labeled synthetic dataset This enabled humanoid robots to perform 22 novel behaviors – such as pouring, opening/closing articulated objects, and manipulating a variety of tools. The original teleoperation dataset only included pick-and-place tasks. This takes task extensibility to another level without requiring human teleoperation for every single task. The pipeline will be made open-source soon. Project page:

The Humanoid Hub

12,074 görüntüleme • 1 yıl önce

What’s else is new on the upcoming Testnet V2? dApps across DeFi, InfoFi, Social, Gaming, Gambling and more… Actions across these dApps will earn you XP. More on it, later. Stay tuned.
0:30

What’s else is new on the upcoming Testnet V2? dApps across DeFi, InfoFi, Social, Gaming, Gambling and more… Actions across these dApps will earn you XP. More on it, later. Stay tuned.

Incentiv

77,208 görüntüleme • 9 ay önce

While working on new update I figured out a completely new way of writing text on prop in much cheaper way and which allows more cool stuff :) Stay tuned, soon new update will be released. Just need to tweak some things when I have time.
1:46

While working on new update I figured out a completely new way of writing text on prop in much cheaper way and which allows more cool stuff :) Stay tuned, soon new update will be released. Just need to tweak some things when I have time.

AsicsoN

13,658 görüntüleme • 1 ay önce