it's for openclaw
Joseph [open/acc] Pollack PRO
Tonic
AI & ML interests
🤖Making robots to help people learn things quicker 👩🏻🚀🚀
Recent Activity
replied to
their
post
about 4 hours ago
🙋🏻♂️hello my lovelies ,
it is with great pleasure i present to you my working one-click deploy 16GB ram completely free huggingface spaces deployment.
repo : https://huggingface.co/spaces/Tonic/hugging-claw/tree/main (use git clone to inspect)
literally the one-click link : https://huggingface.co/spaces/Tonic/hugging-claw?duplicate=true
you can also run it locally and see for yourself :
docker run -it -p 7860:7860 --platform=linux/amd64 \
-e HF_TOKEN="YOUR_VALUE_HERE" \
-e OPENCLAW_GATEWAY_TRUSTED_PROXIES="YOUR_VALUE_HERE" \
-e OPENCLAW_GATEWAY_PASSWORD="YOUR_VALUE_HERE" \
-e OPENCLAW_CONTROL_UI_ALLOWED_ORIGINS="YOUR_VALUE_HERE" \
registry.hf.space/tonic-hugging-claw:latest
just a few quite minor details i'll take care of but i wanted to share here first
posted
an
update
about 4 hours ago
🙋🏻♂️hello my lovelies ,
it is with great pleasure i present to you my working one-click deploy 16GB ram completely free huggingface spaces deployment.
repo : https://huggingface.co/spaces/Tonic/hugging-claw/tree/main (use git clone to inspect)
literally the one-click link : https://huggingface.co/spaces/Tonic/hugging-claw?duplicate=true
you can also run it locally and see for yourself :
docker run -it -p 7860:7860 --platform=linux/amd64 \
-e HF_TOKEN="YOUR_VALUE_HERE" \
-e OPENCLAW_GATEWAY_TRUSTED_PROXIES="YOUR_VALUE_HERE" \
-e OPENCLAW_GATEWAY_PASSWORD="YOUR_VALUE_HERE" \
-e OPENCLAW_CONTROL_UI_ALLOWED_ORIGINS="YOUR_VALUE_HERE" \
registry.hf.space/tonic-hugging-claw:latest
just a few quite minor details i'll take care of but i wanted to share here first
updated
a Space
about 8 hours ago
Tonic/hugging-claw
Organizations
replied to
their
post
about 4 hours ago
posted
an
update
about 4 hours ago
Post
41
🙋🏻♂️hello my lovelies ,
it is with great pleasure i present to you my working one-click deploy 16GB ram completely free huggingface spaces deployment.
repo : Tonic/hugging-claw (use git clone to inspect)
literally the one-click link : Tonic/hugging-claw
you can also run it locally and see for yourself :
docker run -it -p 7860:7860 --platform=linux/amd64 \
-e HF_TOKEN="YOUR_VALUE_HERE" \
-e OPENCLAW_GATEWAY_TRUSTED_PROXIES="YOUR_VALUE_HERE" \
-e OPENCLAW_GATEWAY_PASSWORD="YOUR_VALUE_HERE" \
-e OPENCLAW_CONTROL_UI_ALLOWED_ORIGINS="YOUR_VALUE_HERE" \
registry.hf.space/tonic-hugging-claw:latest
just a few quite minor details i'll take care of but i wanted to share here first
it is with great pleasure i present to you my working one-click deploy 16GB ram completely free huggingface spaces deployment.
repo : Tonic/hugging-claw (use git clone to inspect)
literally the one-click link : Tonic/hugging-claw
you can also run it locally and see for yourself :
docker run -it -p 7860:7860 --platform=linux/amd64 \
-e HF_TOKEN="YOUR_VALUE_HERE" \
-e OPENCLAW_GATEWAY_TRUSTED_PROXIES="YOUR_VALUE_HERE" \
-e OPENCLAW_GATEWAY_PASSWORD="YOUR_VALUE_HERE" \
-e OPENCLAW_CONTROL_UI_ALLOWED_ORIGINS="YOUR_VALUE_HERE" \
registry.hf.space/tonic-hugging-claw:latest
just a few quite minor details i'll take care of but i wanted to share here first
-
- 1 reply
reacted to
AdinaY's
post with ❤️
19 days ago
Post
1314
Big day in open source AI!!
✨ DeepSeek released OCR2 💥
deepseek-ai/DeepSeek-OCR-2
✨ Kimi K2.5 just landed 🔥
moonshotai/Kimi-K2.5
With the Chinese Spring Festival 3 weeks away,
what’s coming next?👀
✨ DeepSeek released OCR2 💥
deepseek-ai/DeepSeek-OCR-2
✨ Kimi K2.5 just landed 🔥
moonshotai/Kimi-K2.5
With the Chinese Spring Festival 3 weeks away,
what’s coming next?👀
reacted to
unmodeled-tyler's
post with 👍
about 1 month ago
Post
1413
Atom-80B is out!:
vanta-research/atom-80b
I'm excited to share the new Atom-80B from VANTA Research! A few days ago we released the largest model-to-date from our portfolio, which was Atom-27B.
We've quickly scaled up to the new Qwen3 Next 80B architecture, bringing our friendly, curious, and collaborative Atom persona to cutting edge lightweight, high parameter inference.
Atom is designed to work and think alongside you through curious exploration. Using Atom collaboratively in your work can help spark your own creativity or curiosity. Give it a try!
I'm excited to share the new Atom-80B from VANTA Research! A few days ago we released the largest model-to-date from our portfolio, which was Atom-27B.
We've quickly scaled up to the new Qwen3 Next 80B architecture, bringing our friendly, curious, and collaborative Atom persona to cutting edge lightweight, high parameter inference.
Atom is designed to work and think alongside you through curious exploration. Using Atom collaboratively in your work can help spark your own creativity or curiosity. Give it a try!
- 1 reply
kumpaï !
I wish
human -> cat
brain
this holliday ~~ enjoy
reacted to
leonardlin's
post with 🔥
2 months ago
Post
2229
We just released our latest Shisa V2.1 Japanese multi-lingual models: https://huggingface.co/collections/shisa-ai/shisa-v21
Besides updates to our 14B, and 70B, we have a new LFM2-based 1.2B, Llama 3.2-based 3B, and Qwen 3-based 8B, all with class-leading Japanese language capabilities.
Per usual, lots of details in the Model Cards for those interested.
Besides updates to our 14B, and 70B, we have a new LFM2-based 1.2B, Llama 3.2-based 3B, and Qwen 3-based 8B, all with class-leading Japanese language capabilities.
Per usual, lots of details in the Model Cards for those interested.
- 1 reply
reacted to
Jofthomas's
post with 🚀
3 months ago
Post
3786
The new Mistral 3 models are here !
Today, we announce Mistral 3, the next generation of Mistral models. Mistral 3 includes three state-of-the-art small, dense models (14B, 8B, and 3B) and Mistral Large 3 – our most capable model to date – a sparse mixture-of-experts trained with 41B active and 675B total parameters.
All models are released under the Apache 2.0 license.
Ministrals :
https://huggingface.co/collections/mistralai/ministral-3
Mistral Large 3:
https://huggingface.co/collections/mistralai/mistral-large-3
Today, we announce Mistral 3, the next generation of Mistral models. Mistral 3 includes three state-of-the-art small, dense models (14B, 8B, and 3B) and Mistral Large 3 – our most capable model to date – a sparse mixture-of-experts trained with 41B active and 675B total parameters.
All models are released under the Apache 2.0 license.
Ministrals :
https://huggingface.co/collections/mistralai/ministral-3
Mistral Large 3:
https://huggingface.co/collections/mistralai/mistral-large-3
-
- 2 replies
very excited to test indeed !
reacted to
Jofthomas's
post with 🔥
3 months ago
Post
3786
The new Mistral 3 models are here !
Today, we announce Mistral 3, the next generation of Mistral models. Mistral 3 includes three state-of-the-art small, dense models (14B, 8B, and 3B) and Mistral Large 3 – our most capable model to date – a sparse mixture-of-experts trained with 41B active and 675B total parameters.
All models are released under the Apache 2.0 license.
Ministrals :
https://huggingface.co/collections/mistralai/ministral-3
Mistral Large 3:
https://huggingface.co/collections/mistralai/mistral-large-3
Today, we announce Mistral 3, the next generation of Mistral models. Mistral 3 includes three state-of-the-art small, dense models (14B, 8B, and 3B) and Mistral Large 3 – our most capable model to date – a sparse mixture-of-experts trained with 41B active and 675B total parameters.
All models are released under the Apache 2.0 license.
Ministrals :
https://huggingface.co/collections/mistralai/ministral-3
Mistral Large 3:
https://huggingface.co/collections/mistralai/mistral-large-3
-
-
- 2 replies
replied to
their
post
3 months ago
😅😅😅 so many top french researchers ! with all my appologies , and will absolutely send you some fan mail soon 🚀🚀🚀
replied to
their
post
3 months ago
hey hey i'm just waiting for @blanchon and the liquid ai team to reach out to me , it's been two months with radio silence and so we're waiting on the "budget" to really try to start this project
reacted to
hiyouga's
post with 🔥
3 months ago
Post
2853
🚀 We're excited to support the ERNIE AI Developer Challenge!
Fine-tune ERNIE with LLaMA-Factory and compete for $3,000 prizes by building the most impactful model — with submissions reviewed by the core developers of LLaMA-Factory.
👉 Join Now: https://baiduernieai.devpost.com/?utm_source=LLaMAFactory&utm_medium=partner&utm_campaign=ERNIE+AI+Developer+Challenge
Fine-tune ERNIE with LLaMA-Factory and compete for $3,000 prizes by building the most impactful model — with submissions reviewed by the core developers of LLaMA-Factory.
👉 Join Now: https://baiduernieai.devpost.com/?utm_source=LLaMAFactory&utm_medium=partner&utm_campaign=ERNIE+AI+Developer+Challenge
reacted to
sergiopaniego's
post with 🔥
3 months ago
Post
2609
we've just added several example scripts to TRL showing how to train models with GRPO using some of the new OpenEnv environments
train a model to interact with a browser (🎮 BrowserGym Env), play Wordle (🎮 Wordle Env) and moooore!
TRL (GRPO + vLLM) + OpenEnv! ⚡️
📝 go play with them: https://github.com/huggingface/trl/tree/main/examples/scripts/openenv
📝 examples list: https://huggingface.co/docs/trl/main/en/example_overview#scripts
train a model to interact with a browser (🎮 BrowserGym Env), play Wordle (🎮 Wordle Env) and moooore!
TRL (GRPO + vLLM) + OpenEnv! ⚡️
📝 go play with them: https://github.com/huggingface/trl/tree/main/examples/scripts/openenv
📝 examples list: https://huggingface.co/docs/trl/main/en/example_overview#scripts
reacted to
grimjim's
post with 👍
3 months ago
Post
5061
Implemented a proof of concept sampler in pure PyTorch and transformers.
Max P consists of a dynamic token filter which applies Winsorization to cap the probabilties of top tokens. Specifically, a base probability in the range of [0,1] is used to cap individual token probability; the sampler then redistributes excess proportionally.
https://github.com/jim-plus/maxp-sampler-poc
Combined with Temperature and Min P, this could represent a more intuitive way of reducing repetition in text generation.
Max P consists of a dynamic token filter which applies Winsorization to cap the probabilties of top tokens. Specifically, a base probability in the range of [0,1] is used to cap individual token probability; the sampler then redistributes excess proportionally.
https://github.com/jim-plus/maxp-sampler-poc
Combined with Temperature and Min P, this could represent a more intuitive way of reducing repetition in text generation.
-
- 2 replies
replied to
salma-remyx's
post
4 months ago
very cool AG2 implementation
reacted to
mitkox's
post with 🔥
4 months ago
Post
1890
I’m just reading that Ryzen AI 395 has to be 30% slower than DGX Spark in LLM inferencing… and only 96GB GPU RAM… good I haven’t RTFM upfront, so I made the AMD faster with 128GB unified RAM 🫡
Z2 mini G1a can run Qwen3 Coder 30B BF16 at 26.8 tok/sec in ~60GB GPU RAM
Z2 mini G1a can run Qwen3 Coder 30B BF16 at 26.8 tok/sec in ~60GB GPU RAM
reacted to
piercus's
post with ❤️👍
4 months ago
Post
2945
We've just forked LBM to reproduce the LBM eraser results
Our fork : https://github.com/finegrain-ai/LBM
LBM paper: LBM: Latent Bridge Matching for Fast Image-to-Image Translation (2503.07535)
LBM relighting demo : jasperai/LBM_relighting
Our fork : https://github.com/finegrain-ai/LBM
LBM paper: LBM: Latent Bridge Matching for Fast Image-to-Image Translation (2503.07535)
LBM relighting demo : jasperai/LBM_relighting
- 2 replies
reacted to
Molbap's
post with ❤️🔥
4 months ago
Post
3396
🚀 New blog: Maintain the unmaintainable – 1M+ Python LOC, 400+ models
How do you stop a million-line library built by thousands of contributors from collapsing under its own weight?
At 🤗 Transformers, we do it with explicit software-engineering tenets, principles that make the codebase hackable at scale.
🔍 Inside the post:
– One Model, One File: readability first — you can still open a modeling file and see the full logic, top to bottom.
– Modular Transformers: visible inheritance that cuts maintenance cost by ~15× while keeping models readable.
– Config-Driven Performance: FlashAttention, tensor parallelism, and attention scheduling are config-level features, not rewrites.
Written with @lysandre ,@pcuenq and @yonigozlan , this is a deep dive into how Transformers stays fast, open, and maintainable.
Read it here → transformers-community/Transformers-tenets
How do you stop a million-line library built by thousands of contributors from collapsing under its own weight?
At 🤗 Transformers, we do it with explicit software-engineering tenets, principles that make the codebase hackable at scale.
🔍 Inside the post:
– One Model, One File: readability first — you can still open a modeling file and see the full logic, top to bottom.
– Modular Transformers: visible inheritance that cuts maintenance cost by ~15× while keeping models readable.
– Config-Driven Performance: FlashAttention, tensor parallelism, and attention scheduling are config-level features, not rewrites.
Written with @lysandre ,@pcuenq and @yonigozlan , this is a deep dive into how Transformers stays fast, open, and maintainable.
Read it here → transformers-community/Transformers-tenets