36 1 9

s

Tom-Neverwinter

Tom-Neverwinter

AI & ML interests

Making improvements to help the world.

Recent Activity

reacted to branikita's post with 🔥 23 days ago

https://robonine.com/testing-of-feetech-sts3215-servomotor-backlash-repeatability-and-torque/ 🤖 New article: In-depth testing of the Feetech STS3215 servomotor — the popular choice for open-source robotic projects like SO-ARM 100 and others. We've conducted comprehensive performance analysis covering backlash, repeatability, torque characteristics, and thermal behavior. Discover how this affordable servo performs in real-world robotic applications, including its 12-bit magnetic encoder, metal gearbox design, and overload protection mechanisms. #Robotics #Servomotor #EngineeringTesting #Automation #FeetechSTS3215 #OpenSourceRobotics #SOArm #RoboticSystems #ControlSystems #MotorTesting #AffordableRobotics #ClosedLoopControl

new activity about 2 months ago

BeaverAI/Anubis-Mini-8B-v1a-GGUF:recommended prompt

new activity about 2 months ago

Qwen/Qwen3-Omni-30B-A3B-Instruct:Example of how to set up Qwen3-omni for audio-input audio-output

View all activity

Organizations

None yet

reacted to branikita's post with 🔥 23 days ago

Post

3263

https://robonine.com/testing-of-feetech-sts3215-servomotor-backlash-repeatability-and-torque/

🤖 New article: In-depth testing of the Feetech STS3215 servomotor — the popular choice for open-source robotic projects like SO-ARM 100 and others. We've conducted comprehensive performance analysis covering backlash, repeatability, torque characteristics, and thermal behavior. Discover how this affordable servo performs in real-world robotic applications, including its 12-bit magnetic encoder, metal gearbox design, and overload protection mechanisms.
#Robotics #Servomotor #EngineeringTesting #Automation #FeetechSTS3215 #OpenSourceRobotics #SOArm #RoboticSystems #ControlSystems #MotorTesting #AffordableRobotics #ClosedLoopControl

New activity in BeaverAI/Anubis-Mini-8B-v1a-GGUF about 2 months ago

recommended prompt

#1 opened about 2 months ago by

Tom-Neverwinter

New activity in Qwen/Qwen3-Omni-30B-A3B-Instruct about 2 months ago

Example of how to set up Qwen3-omni for audio-input audio-output

👍 🔥 9

#2 opened about 2 months ago by

abidlabs

New activity in nvidia/parakeet-tdt-0.6b-v3 about 2 months ago

Japanese support plan?

👍 5

#5 opened 3 months ago by

sttt

New activity in ReadyArt/Safeword-Casual-V1-12B-GGUF 2 months ago

Anything special?

😎 1

#1 opened 2 months ago by

Tom-Neverwinter

New activity in nvidia/parakeet-rnnt-1.1b 5 months ago

Support translation

#3 opened almost 2 years ago by

SyedAbdul

replied to Kseniase's post 5 months ago

Honestly I dont understand why we are trying to cram everything into one model and not making them in slices. a slice for vision a slice for interaction a slice for art or image generation a slice for audio or voice a slice for math a slice for history and so on and so forth

New activity in BeaverAI/Test-12B-v1b-GGUF 5 months ago

another new model :)

#1 opened 5 months ago by

Tom-Neverwinter

reacted to drwlf's post with ❤️🤗 5 months ago

Post

5738

Having an insanely good medical LLM is pointless if it won’t answer your questions!

So we’ve made 2 notebook for abliterating any model in order to achieve a good model that will actually help you!

The notebooks are made using @mlabonne ‘s abliteration logic and datasets!

Feel free to use them and happy training 😊

https://github.com/dralexlup/LLM-Abliteration

3 replies

reacted to fdaudens's post with ❤️ 6 months ago

Post

2507

Here’s what happens when a national institution builds its own digital intelligence: France’s Ministry of Culture just released 17K+ real users testing 30+ chatbots in French. Raw, diverse, and a goldmine for studying LLMs in the wild.

ministere-culture/comparia-conversations

reacted to prithivMLmods's post with 🤗 6 months ago

Post

2378

The more optimized explicit content filters with lightweight 𝙜𝙪𝙖𝙧𝙙 models trained based on siglip2 patch16 512 and vit patch16 224 for illustration and explicit content classification for content moderation in social media, forums, and parental controls for safer browsing environments. this version fixes the issues in the previous release, which lacked sufficient resources. 🚀

⤷ Models :
→ siglip2 mini explicit content : prithivMLmods/siglip2-mini-explicit-content [recommended]
→ vit mini explicit content : prithivMLmods/vit-mini-explicit-content

⤷ Building image safety-guard models :

strangerguardhf

⤷ Datasets :
→ nsfw multidomain classification : strangerguardhf/NSFW-MultiDomain-Classification
→ nsfw multidomain classification v2.0 : strangerguardhf/NSFW-MultiDomain-Classification-v2.0

⤷ Collection :
→ Updated Versions [05192025] : prithivMLmods/explicit-content-filters-682aaa4733e378561925ca2b
→ Previous Versions : prithivMLmods/siglip2-content-filters-042025-final-680fe4aa1a9d589bf2c915ff

Find a collections inside the collection.👆

To know more about it, visit the model card of the respective model.

1 reply

replied to prithivMLmods's post 6 months ago

"lightweight 𝙜𝙪𝙖𝙧𝙙" models is what I want to hear. I'm sick and tired of models so locked down they may as well be useless. If I cant play D&D on your model you should shove it in the trash as you failed. Then again we have mark zuckerberg who cant cut down on white supremacy or basic spam to save his life.

replied to reach-vb's post 6 months ago

good news for the community!

reacted to reach-vb's post with ❤️🔥👍 6 months ago

Post

4591

hey hey @mradermacher - VB from Hugging Face here, we'd love to onboard you over to our optimised xet backend! 💥

as you know we're in the process of upgrading our storage backend to xet (which helps us scale and offer blazingly fast upload/ download speeds too): https://huggingface.co/blog/xet-on-the-hub and now that we are certain that the backend can scale with even big models like Llama 4/ Qwen 3 - we;re moving to the next phase of inviting impactful orgs and users on the hub over as you are a big part of the open source ML community - we would love to onboard you next and create some excitement about it in the community too!

in terms of actual steps - it should be as simple as one of the org admins to join hf.co/join/xet - we'll take care of the rest.

p.s. you'd need to have a the latest hf_xet version of huggingface_hub lib but everything else should be the same: https://huggingface.co/docs/hub/storage-backends#using-xet-storage

p.p.s. this is fully backwards compatible so everything will work as it should! 🤗

16 replies

New activity in Qwen/Qwen2.5-Omni-7B 6 months ago

GGUF model

#51 opened 6 months ago by

Tom-Neverwinter

reacted to Zherui's post with 🤗🔥 7 months ago

Post

1939

⏰ The #CVPR2025 submission deadline is approaching fast — don't forget to upload your results by May 10th! Right after CVPR, the #ICCV2025 season begins.

🤖 Coming in early May: The AgiBot World Challenge!
In this challenge, we are going beyond the lab and into the real world — deploying them on real robots, live at #IROS2025.

🔗 Learn more at http://opendrivelab.com/challenge2025

s

AI & ML interests

Recent Activity

Organizations

Tom-Neverwinter's activity

recommended prompt

Example of how to set up Qwen3-omni for audio-input audio-output

Japanese support plan?

Anything special?

Support translation

another new model :)

GGUF model