huggingface-projects/Deep-RL-Course-Certification
Viewer
•
Updated
•
1.59k
•
258
•
15
AI & ML interests
None defined yet.
Recent Activity
View all activity
sergiopaniego
updated
a
dataset
about 21 hours ago
Post
955
Cool stuff these past weeks on huggingface! 🤗 🚀 !
• 📈Trackio, local-first W&B alternative
https://github.com/gradio-app/trackio/issues
• 🌍EmbeddingGemma, 300M-param, multilingual embeddings, on-device
https://huggingface.co/blog/embeddinggemma
• 💻Open LLMs in VS Code (Inference Providers)
https://x.com/reach_vb/status/1966185427582497171
• 🤖Smol2Operator GUI agents
https://huggingface.co/blog/smol2operator
• 🖼️Gradio visible watermarking
https://huggingface.co/blog/watermarking-with-gradio
• 📈Trackio, local-first W&B alternative
https://github.com/gradio-app/trackio/issues
• 🌍EmbeddingGemma, 300M-param, multilingual embeddings, on-device
https://huggingface.co/blog/embeddinggemma
• 💻Open LLMs in VS Code (Inference Providers)
https://x.com/reach_vb/status/1966185427582497171
• 🤖Smol2Operator GUI agents
https://huggingface.co/blog/smol2operator
• 🖼️Gradio visible watermarking
https://huggingface.co/blog/watermarking-with-gradio
sergiopaniego
posted
an
update
about 24 hours ago
Post
1822
A few days ago, Thinking Machines Lab released “LoRA Without Regret”, showing that LoRA can match full fine-tuning performance when configured right.
Naturally, we decided to reproduce the results with TRL and release a guide!
https://huggingface.co/docs/trl/main/en/lora_without_regret
Naturally, we decided to reproduce the results with TRL and release a guide!
https://huggingface.co/docs/trl/main/en/lora_without_regret
Post
251
Qwen never stops🤯
Meet Qwen3-VL-30B-A3B-Thinking & Instruct 🔥
Qwen/Qwen3-VL-30B-A3B-Instruct
Qwen/Qwen3-VL-30B-A3B-Thinking
✨256K–1M context for long docs & video
✨32 language OCR & stronger visual recognition
✨“Visual Agent” that operates GUIs
Meet Qwen3-VL-30B-A3B-Thinking & Instruct 🔥
Qwen/Qwen3-VL-30B-A3B-Instruct
Qwen/Qwen3-VL-30B-A3B-Thinking
✨256K–1M context for long docs & video
✨32 language OCR & stronger visual recognition
✨“Visual Agent” that operates GUIs
Post
408
New release from Ant Group 🔥
inclusionAI/ming-v2-68ddea4954413c128d706630
✨MingTok (Vision & Audio): continuous unified tokenizer, no quantization, preserves semantic & perceptual fidelity, enables faster convergence.
✨Ming-UniVision: MLLM unifying image understanding + generation, supports multi-round editing & visualized CoT.
✨Ming-UniAudio: unified speech LLM for ASR, TTS & free-form editing, integrates semantic + acoustic features for high-fidelity audio.
inclusionAI/ming-v2-68ddea4954413c128d706630
✨MingTok (Vision & Audio): continuous unified tokenizer, no quantization, preserves semantic & perceptual fidelity, enables faster convergence.
✨Ming-UniVision: MLLM unifying image understanding + generation, supports multi-round editing & visualized CoT.
✨Ming-UniAudio: unified speech LLM for ASR, TTS & free-form editing, integrates semantic + acoustic features for high-fidelity audio.
Post
446
🔥 September highlights from Chinese open source community
zh-ai-community/september-2025-china-open-source-highlights-68b55c9e757c439ad9dd6aba
✨ Massive releases from the two tech giants
- At Alibaba Cloud Summit, Qwen dropped at least 7 new series of models. ( some are not open sourced )
- Since June, Tencent has doubled down on open source, especially after Hunyuan gained traction
✨ Some of the community’s hottest models come from startups.
- Kimi K2-0905
- GLM v4.6
-OpenBMB MiniCPM 4.1
✨ New players are pushing hard!
- Baidu ERNIE & Qianfan: enterprise-ready focus
- Ant Group: MoE + low-activation; from small to trillion, from core to reasoning fast track
- Xiaomi MiMo: stands out with Any-to-Any audio models
✨ Robotics is joining the open-source wave
- Unitree released its first open-source model
- BAAI launched RoboBrain-X0, an open-source robotics model + dataset
👀 Each month brings cooler models. After the 8-day National Holiday, expect another wave before the end of the year.
Stay tuned!
zh-ai-community/september-2025-china-open-source-highlights-68b55c9e757c439ad9dd6aba
✨ Massive releases from the two tech giants
- At Alibaba Cloud Summit, Qwen dropped at least 7 new series of models. ( some are not open sourced )
- Since June, Tencent has doubled down on open source, especially after Hunyuan gained traction
✨ Some of the community’s hottest models come from startups.
- Kimi K2-0905
- GLM v4.6
-OpenBMB MiniCPM 4.1
✨ New players are pushing hard!
- Baidu ERNIE & Qianfan: enterprise-ready focus
- Ant Group: MoE + low-activation; from small to trillion, from core to reasoning fast track
- Xiaomi MiMo: stands out with Any-to-Any audio models
✨ Robotics is joining the open-source wave
- Unitree released its first open-source model
- BAAI launched RoboBrain-X0, an open-source robotics model + dataset
👀 Each month brings cooler models. After the 8-day National Holiday, expect another wave before the end of the year.
Stay tuned!
sergiopaniego
posted
an
update
6 days ago
Post
471
Want to deploy open models using vLLM as the inference engine?
We just released a step-by-step guide on how to do it with @huggingface Inference Endpoints, now available in the vLLM docs.
let the gpus go brrr
https://docs.vllm.ai/en/latest/deployment/frameworks/hf_inference_endpoints.html
We just released a step-by-step guide on how to do it with @huggingface Inference Endpoints, now available in the vLLM docs.
let the gpus go brrr
https://docs.vllm.ai/en/latest/deployment/frameworks/hf_inference_endpoints.html
pcuenq
updated
a
dataset
6 days ago
Post
2647
GLM-4.6 is here🚀
zai-org/GLM-4.6
✨ 200K context window
✨ Superior coding & polished UI generation
✨ Stronger reasoning & tool use
✨ More capable agents & agent frameworks
zai-org/GLM-4.6
✨ 200K context window
✨ Superior coding & polished UI generation
✨ Stronger reasoning & tool use
✨ More capable agents & agent frameworks
Post
337
MOSS-Speech 🔊 bilingual native speech-to-speech model, from Fudan University.
fnlp/moss-speech-68dbab23bc98501afede0cd3
✨ Supports Chinese & English
✨ Layer-splitting architecture + frozen pretraining
✨ Preserves tone, emotion & prosody
fnlp/moss-speech-68dbab23bc98501afede0cd3
✨ Supports Chinese & English
✨ Layer-splitting architecture + frozen pretraining
✨ Preserves tone, emotion & prosody
Post
352
RoboBrain-X0- Preview 🤖 a unified cross-embodiment VLA model from
BAAI.
BAAI/robobrain-x0-68db67d3542e04c5d99f31f9
✨Zero-shot generalization across heterogeneous robots
✨Complex task decomposition & embodied reasoning
✨Unified Action Vocabulary + OmniSAT tokenizer
✨End-to-end: perception > reasoning > execution
✨Full version coming soon 🔥
BAAI.
BAAI/robobrain-x0-68db67d3542e04c5d99f31f9
✨Zero-shot generalization across heterogeneous robots
✨Complex task decomposition & embodied reasoning
✨Unified Action Vocabulary + OmniSAT tokenizer
✨End-to-end: perception > reasoning > execution
✨Full version coming soon 🔥
Post
1480
Ring-1T-preview 🔥 1T thinking model released by Ant Group.
inclusionAI/Ring-1T-preview
✨ MoE architecture + 20T tokens + RLVR via ASystem
✨ Strong natural language reasoning (AIME’25: 92.6, close to GPT-5)
✨IMO tests: advanced problem-solving & reasoning
inclusionAI/Ring-1T-preview
✨ MoE architecture + 20T tokens + RLVR via ASystem
✨ Strong natural language reasoning (AIME’25: 92.6, close to GPT-5)
✨IMO tests: advanced problem-solving & reasoning
Post
10620
One of the hardest challenges in AI safety is finding the right balance: how do we protect people from harm without undermining their agency? This tension is especially visible in conversational systems, where safeguards can sometimes feel more paternalistic than supportive.
In my latest piece for Hugging Face, I argue that open source and community-driven approaches offer a promising (though not exclusive) way forward.
✨ Transparency can make safety mechanisms into learning opportunities.
✨ Collaboration with diverse communities makes safeguards more relevant across contexts.
✨ Iteration in the open lets protections evolve rather than freeze into rigid, one-size-fits-all rules.
Of course, this isn’t a silver bullet. Top-down safety measures will still be necessary in some cases. But if we only rely on corporate control, we risk building systems that are safe at the expense of trust and autonomy.
Read the blog post here: https://huggingface.co/blog/giadap/preserving-agency
In my latest piece for Hugging Face, I argue that open source and community-driven approaches offer a promising (though not exclusive) way forward.
✨ Transparency can make safety mechanisms into learning opportunities.
✨ Collaboration with diverse communities makes safeguards more relevant across contexts.
✨ Iteration in the open lets protections evolve rather than freeze into rigid, one-size-fits-all rules.
Of course, this isn’t a silver bullet. Top-down safety measures will still be necessary in some cases. But if we only rely on corporate control, we risk building systems that are safe at the expense of trust and autonomy.
Read the blog post here: https://huggingface.co/blog/giadap/preserving-agency
- 6 replies
Post
1995
Ring-mini-linear-2.0 🔥a hybrid attention MoE model released by Ant group
inclusionAI/Ring-mini-linear-2.0
✨ Hybrid linear + standard attention
✨ 16.4B total, only 1.6B activated
✨ 512k context window via YaRN
✨ Faster than same-size MoE
inclusionAI/Ring-mini-linear-2.0
✨ Hybrid linear + standard attention
✨ 16.4B total, only 1.6B activated
✨ 512k context window via YaRN
✨ Faster than same-size MoE
- 2 replies
Post
398
Hunyuan3D-Part 🔥image-to-3D part generation model released by
Tencent Hunyuan
Weights: tencent/Hunyuan3D-Part
Paper: P3-SAM: Native 3D Part Segmentation (2509.06784)
Demo: tencent/Hunyuan3D-Part
✨ P3-SAM: Native 3D part segmentation with semantic features & bounding boxes
✨ X-Part: High-fidelity, structure-coherent shape decomposition
✨ Handles scanned & AI-generated meshes seamlessly
Tencent Hunyuan
Weights: tencent/Hunyuan3D-Part
Paper: P3-SAM: Native 3D Part Segmentation (2509.06784)
Demo: tencent/Hunyuan3D-Part
✨ P3-SAM: Native 3D part segmentation with semantic features & bounding boxes
✨ X-Part: High-fidelity, structure-coherent shape decomposition
✨ Handles scanned & AI-generated meshes seamlessly
sergiopaniego
posted
an
update
11 days ago
Post
420
You need to try this tool! 🫡
My colleague @Molbap built an interactive HF Space to explore the modular support of open models in transformers over time
👀 You’ll spot things like 🦙 llama defining many models or which ones could be modular next
Try it: Molbap/transformers-modular-refactor
My colleague @Molbap built an interactive HF Space to explore the modular support of open models in transformers over time
👀 You’ll spot things like 🦙 llama defining many models or which ones could be modular next
Try it: Molbap/transformers-modular-refactor
sergiopaniego
posted
an
update
12 days ago
Post
418
How fast can you create an endpoint in Hugging Face Inference Endpoints with a new model + vLLM to deploy a state-of-the-art OCR model?
Let’s break it down step by step.
1️⃣ Create your endpoint
Go to Hugging Face Endpoints → + NEW
Select Deploy from Hub → rednote-hilab/dots.ocr → Configure 🛠️
2️⃣ Configure hardware & container
Pick hardware: AWS/GPU/L4 ⚡
Set container: vLLM 🐇
Click Create ✅
3️⃣ Update endpoint settings
Container: Container URI: vllm/vllm-openai:nightly → Update
Advanced: add flag --trust-remote-code → Update ⚠️
4️⃣ Run inference
Download the script 📝: ariG23498/useful-scripts
Set your HF_TOKEN and update base_url in the script.
Run it. ✅
Your OCR model is now live via HF Inference Endpoints!
Let’s break it down step by step.
1️⃣ Create your endpoint
Go to Hugging Face Endpoints → + NEW
Select Deploy from Hub → rednote-hilab/dots.ocr → Configure 🛠️
2️⃣ Configure hardware & container
Pick hardware: AWS/GPU/L4 ⚡
Set container: vLLM 🐇
Click Create ✅
3️⃣ Update endpoint settings
Container: Container URI: vllm/vllm-openai:nightly → Update
Advanced: add flag --trust-remote-code → Update ⚠️
4️⃣ Run inference
Download the script 📝: ariG23498/useful-scripts
Set your HF_TOKEN and update base_url in the script.
Run it. ✅
Your OCR model is now live via HF Inference Endpoints!
sergiopaniego
posted
an
update
13 days ago
Post
3372
💥 Tons of new material just landed in the smol-course! 🧑💻
> evaluation
> alignment
> VLMs
> quizzes
> assignments!
> certificates!👩🎓
go learn! 👉 https://huggingface.co/learn/smol-course/unit0/1
> evaluation
> alignment
> VLMs
> quizzes
> assignments!
> certificates!👩🎓
go learn! 👉 https://huggingface.co/learn/smol-course/unit0/1
- 1 reply
Post
1930
Qwen3Guard 🛡️ a series of safety moderation models built upon Qwen3
Qwen/qwen3guard-68d2729abbfae4716f3343a1
✨ 0.6B/4B/8B - Apache2.0
✨ Two variants: Gen & Steam
✨ Trained on a dataset of 1.19 million prompts
✨ Classifies content into Safe / Unsafe / Controversial
✨ Supports 119 languages & dialects
Qwen/qwen3guard-68d2729abbfae4716f3343a1
✨ 0.6B/4B/8B - Apache2.0
✨ Two variants: Gen & Steam
✨ Trained on a dataset of 1.19 million prompts
✨ Classifies content into Safe / Unsafe / Controversial
✨ Supports 119 languages & dialects