Hugging Face's logo

gg-hf-g
community
Activity Feed

AI & ML interests

None defined yet.

Recent Activity
osanseviero  authored a paper about 1 month ago
Gemma 4 Technical Report
osanseviero  submitted a paper about 1 month ago
Gemma 4 Technical Report
mrpeerat  authored a paper 6 months ago
SEA-Guard: Culturally Grounded Multilingual Safeguard for Southeast Asia
View all activity
mlabonne 
posted an update 7 days ago
view post
Post
3067
Deploy local agents everywhere with LiquidAI/LFM2.5-2.6B

Unlike agents that depend on cloud APIs, local agents give you free inference, low latency, and real privacy.

Removing the per-token cost changes how developers build: agents can now be massively parallelized on local hardware, running background tasks that burn through millions of tokens at no marginal cost!
  • 7 replies
·
osanseviero 
authored a paper about 1 month ago
osanseviero 
submitted a paper to Daily Papers about 1 month ago
alvarobartt 
posted an update 3 months ago
view post
Post
538
Open agents on AWS SageMaker AI with open models from the Hugging Face Hub!

> Deploy an open model from the Hugging Face Hub on SageMaker AI
> Connect the deployed model to Strands Agents
> Add built-in and custom tools for tool calling
> Expose external capabilities through MCP integration
> Bonus: talk to your agent and visualize traces with Gradio

https://alvarobartt.com/agents-on-aws-sagemaker
alvarobartt 
posted an update 3 months ago
view post
Post
3379
Latest hf-mem release added a breakdown of Mixture-of-Experts (MoE) memory usage!

TL; DR MoEs can be misleading to reason about from active parameters alone, since each token only activates a subset of experts, while the serving setup still needs to account for the full resident memory footprint.

🧠 hf-mem now splits MoE memory into base model weights, routed experts, and KV cache
🏗️ Dense models usually load and use most weights every forward pass, while MoEs load many experts but only route each token to a few of them
⚡ Active params isn't the same as memory footprint, especially for sparse architectures
📦 Runtime memory is about what is used per request/token, while loading memory also includes the expert weights that need to be resident
📚 KV cache can still dominate depending on context length, batch size, and concurrency
🔀 Expert Parallelism (EP) helps shard experts across accelerators when expert weights dominate
🚀 Data Parallelism (DP) + EP is often a good fit for throughput-oriented MoE serving

Check the repository at https://github.com/alvarobartt/hf-mem
mlabonne 
posted an update 4 months ago
view post
Post
4835
Big update to llm-datasets, my curated list of datasets and tools for post-training LLMs.

> Added many new datasets
> New "thinking" column
> Refreshed recommended tools.

Thanks to everyone who told me they used it for their research at ICLR, you motivated this update!
  • 2 replies
·
alvarobartt 
posted an update 5 months ago
view post
Post
3772
Learn how to deploy Microsoft Research VibeVoice ASR on Microsoft Azure Foundry with Hugging Face to generate rich audio transcriptions with Who, When, and What! 💥

> 🕒 60-minute single-pass processing, no chunking or stitching
> 👤 Customized hotwords to guide recognition on domain-specific content
> 📝 Rich transcription: joint ASR + diarization + timestamping in one pass
> 🌍 50+ languages with automatic detection and code-switching support
> 🤗 Deployed on Microsoft Foundry via an OpenAI-compatible Chat Completions API

https://huggingface.co/docs/microsoft-azure/foundry/examples/deploy-vibevoice-asr
mrpeerat 
authored 2 papers 6 months ago
mrpeerat 
submitted a paper to Daily Papers 6 months ago
alvarobartt 
posted an update 7 months ago
view post
Post
3307
💥 hf-mem v0.4.1 now also estimates KV cache memory requirements for any context length and batch size with the --experimental flag!

uvx hf-mem --model-id ... --experimental will automatically pull the required information from the Hugging Face Hub to include the KV cache estimation, when applicable.

💡 Alternatively, you can also set the --max-model-len, --batch-size and --kv-cache-dtype arguments (à la vLLM) manually if preferred.
  • 1 reply
·
mlabonne 
authored 2 papers 7 months ago
RyanMullins 
authored a paper 7 months ago
mlabonne 
posted an update 7 months ago
alozowski 
authored a paper 8 months ago
merve 
posted an update 10 months ago
view post
Post
14384
deepseek-ai/DeepSeek-OCR is out! 🔥 my take ⤵️
> pretty insane it can parse and re-render charts in HTML
> it uses CLIP and SAM features concatenated, so better grounding
> very efficient per vision tokens/performance ratio
> covers 100 languages
  • 5 replies
·
mlabonne 
posted an update 10 months ago
view post
Post
8505
LiquidAI/LFM2-8B-A1B just dropped!

8.3B params with only 1.5B active/token 🚀

> Quality ≈ 3–4B dense, yet faster than Qwen3-1.7B
> MoE designed to run on phones/laptops (llama.cpp / vLLM)
> Pre-trained on 12T tokens → strong math/code/IF
  • 1 reply
·
michellecasbon 
authored a paper 10 months ago
mlabonne 
posted an update 11 months ago
view post
Post
3942
⚛️ New drop of tiny task-specific models!

Want to do data extraction, translation, RAG, tool use, or math on a Raspberry Pi? We got you covered! ✅

These tiny models were fine-tuned to perform narrow tasks extremely well, making them competitive with much larger models.

You can deploy them today on-device or even on GPUs for big data operations!

LiquidAI/liquid-nanos-68b98d898414dd94d4d5f99a
  • 1 reply
·