AI & ML interests

Democratizar el PLN en español creando recursos abiertos en nuestro idioma🚀

Recent Activity

davidquicast 
posted an update 4 days ago
view post
Post
79
🤬Multilingual AI models are easier to misuse in low-resource languages.

For the @Lexsi Labs AI Safety and Alignment Hackathon I looked into why this happens in @Cohere 's Tiny Aya Global, and how to fix it without retraining the model.

The short version: the model recognises a harmful request equally well in all ten languages I tested. What weakens outside English is the internal signal that turns that recognition into a refusal. A 33 KB adapter that restores that signal cut harmful answers from 5.4 % to 0.1 % and closed the gap between languages, with no loss in capability or speed.

The full write-up, with the method, results, limitations, an interactive demo and all the open artifacts, is available here:

🤗 https://huggingface.co/blog/davidquicast/xl-refusal-bridge-closing-tiny-aya-cross-lingual-s
alvarobartt 
posted an update 6 months ago
view post
Post
2,360
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 6 months ago
view post
Post
4,738
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
alvarobartt 
posted an update 9 months ago
view post
Post
4,627
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
juanjucm 
posted an update 10 months ago
view post
Post
455
Last week,
zai-org
dropped zai-org/GLM-4.7-Flash. Now, we bring it to Microsoft Foundry!

- 🏆 30B-A3B MoE, the strongest model in the 30B class. It excels at coding tasks, agentic workflows and reasoning.
- 🤏🏻 Lighter version of his 358B big brother, balancing performance and efficiency.

Not light enough for you? We are also adding
unsloth
unsloth/GLM-4.7-Flash-GGUF to the catalog, with GPU and CPU support powered by llama.cpp 🔥

Go join the hype and deploy them from the Hugging Face collection on Microsoft Foundry!
  • 2 replies
·
alvarobartt 
posted an update 10 months ago
view post
Post
3,870
💥 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
·
davidquicast 
posted an update 11 months ago
view post
Post
4,369
Check out your 2025 Hugging Face Wrapped, a small experimental recap
hf-wrapped/2025
  • 3 replies
·
davidquicast 
posted an update about 1 year ago
view post
Post
2,909
Just applied for HF Community Grant for “Hugging Research” — a lightweight CodeAgent‑based research assistant built on Hugging Face’s Open Deep Research project for the Hugging Face Hub (models, datasets, Spaces, users, collections, papers). It gathers links via dedicated tools and organizes them for easy review.

As this is for the community, comments and suggestions are appreciated: https://huggingface.co/spaces/daqc/hugging-research/discussions/1#68a94d9bcb035c54bc671119