SomosNLP

non-profit

https://somosnlp.org/

SomosNLP_

somosnlp

Activity Feed

AI & ML interests

Democratizar el PLN en español e incentivar su aplicación para generar impacto social 💛

Recent Activity

plaguss authored a paper 5 days ago

SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

mariagrandury updated a collection 7 days ago

Corpus: Evaluation datasets for ES & LATAM

mariagrandury updated a collection 13 days ago

Pre-trained LMs ES

View all activity

somosnlp's activity

davidberenstein1957

posted an update 1 day ago

Post

1245

Fine-tune Deepseek-R1 with a Synthetic Reasoning Dataset

Blog: https://huggingface.co/blog/sdiazlor/fine-tune-deepseek-with-a-synthetic-reasoning-data

davidberenstein1957

posted an update 6 days ago

Post

1873

Agentic RAG: Applied, visual, and step-by-step! 🐾

Get familiar with the Agents and tools, not the bells and whistles!

Retrieve - Augment and now GENERATE.

part 3: https://huggingface.co/blog/davidberenstein1957/ai-blueprint-agentic-rag-part-3-generate

davidberenstein1957

posted an update 7 days ago

Post

2700

Anyone can create free hosted tools for their AI agents! 🔥

Agentic RAG stack part 2 - augment
Augment retrieval results by reranking optimises content without increasing time too much

part2: https://huggingface.co/blog/davidberenstein1957/ai-blueprint-agentic-rag-part-2-augment
code: https://github.com/huggingface/ai-blueprint

albertvillanova

posted an update 7 days ago

Post

2964

🚀 Introducing @huggingface Open Deep-Research💥

In just 24 hours, we built an open-source agent that:
✅ Autonomously browse the web
✅ Search, scroll & extract info
✅ Download & manipulate files
✅ Run calculations on data

55% on GAIA validation set! Help us improve it!💡
https://huggingface.co/blog/open-deep-research

3 replies

mariagrandury

updated a collection 7 days ago

Corpus: Evaluation datasets for ES & LATAM

Collection

Corpus of La Leaderboard, the open LLM leaderboard for ES & LATAM • 56 items • Updated 7 days ago • 3

davidberenstein1957

posted an update 7 days ago

Post

1870

Creating an agentic RAG stack on the Hugging Face Hub - part 1 - retrieval (1/5).

🚀 Web apps and microservices included!

Chunk, embed and index documents at a huge scale without overhead.

Blog: https://huggingface.co/blog/davidberenstein1957/ai-blueprint-agentic-rag-part-1-retrieve

davidberenstein1957

posted an update 13 days ago

Post

1555

tldr; Parquet is awesome, DuckDB too!

Datasets on the Hugging Face Hub rely on parquet files. We can interact with these files using DuckDB as a fast in-memory database system. One of DuckDB’s features is vector similarity search which can be used with or without an index.

blog:
https://huggingface.co/learn/cookbook/vector_search_with_hub_as_backend

mariagrandury

updated 2 collections 13 days ago

Pre-trained LMs ES

Collection

Monolingual language models pre-trained on Spanish and related languages. • 21 items • Updated 7 days ago • 6

Instruction-Tuned Models ES

Collection

Instruction-tuned models in Spanish and other related languages • 8 items • Updated 7 days ago • 4

davidberenstein1957

posted an update 16 days ago

Post

1754

Let's uncover the post-training dataset from DeepSeek-R1 with Magpie!

Pass pre-query tokens <｜begin▁of▁sentence｜>User: , let the model generate the rest.

We can get realistic examples!

Gist: https://gist.github.com/davidberenstein1957/3f20046ce57395a6aba13f8b4e956b59

6 replies

haritzpuerto

posted an update 18 days ago

Post

603

I just got my first ChatGPT review on ARR! 😅 Any advice on how to prove it's AI-generated? Thanks!

3 replies

haritzpuerto

posted an update 19 days ago

Post

1460

I'm excited to announce that my internship paper at Parameter Lab was accepted to Findings of #NAACL2025 🎉
TLDR: Stating an LLM was trained on a sentence might not be possible 😥 , but it is possible for large enough amounts of tokens, such as long documents or multiple documents! 🤯
Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models (2411.00154)
🔗 https://github.com/parameterlab/mia-scaling

davidberenstein1957

posted an update 21 days ago

Post

1869

The RAG's in the bag!

You can now use the Synthetic Data Generator with your own domain-specific seed data to generate a dataset for fine-tuning retrieval or reranking models.

GitHub: https://buff.ly/49IDSmd
Spaces: https://buff.ly/3Y1S99z
Blog: https://huggingface.co/blog/sdiazlor/fine-tune-modernbert-for-rag-with-synthetic-data

1 reply

davidberenstein1957

posted an update 26 days ago

Post

1244

You can now use the "Synthetic Data Generator" at a much larger scale with your preferred inference engine: Ollama, vLLM, TGI, and serverless inference! 🔥

Install, configure, launch!

Space: argilla/synthetic-data-generator
Examples: https://github.com/argilla-io/synthetic-data-generator/tree/main/examples

nataliaElv

posted an update 26 days ago

Post

1450

New chapter in the Hugging Face NLP course! 🤗 🚀

We've added a new chapter about the very basics of Argilla to the Hugging Face NLP course. Learn how to set up an Argilla instance, load & annotate datasets, and export them to the Hub.

Any feedback for improvements welcome!

https://huggingface.co/learn/nlp-course/chapter10

davidberenstein1957

posted an update 28 days ago

Post

2104

🔦 What? The Hub as a vector search backend!

code: https://gist.github.com/davidberenstein1957/f0157a471ec59d9dd44ae6957f1d52ec
build on DuckDB: https://huggingface.co/docs/hub/en/datasets-duckdb

nataliaElv

posted an update about 1 month ago

Post

549

Do you want to easily save annotations to a Dataset in the Hub?

In the last version of Argilla (v2.6.0), you can export your data directly from the UI to the Hub.

Check all the changes and update to the latest version: https://github.com/argilla-io/argilla/releases/tag/v2.6.0

albertvillanova

posted an update about 1 month ago

Post

2053

Discover all the improvements in the new version of Lighteval: https://huggingface.co/docs/lighteval/

davidberenstein1957

posted an update about 1 month ago

Post

1944

Fine-tune a SmolLM on domain-specific synthetic data from a LLM

Blog: https://huggingface.co/blog/davidberenstein1957/fine-tune-a-smollm-on-synthetic-data-of-llm

1 reply

davidberenstein1957

posted an update about 1 month ago

Post

2020

Fine-tuning ModernBERT for text classification using synthetic data generation

From prompt to model in 3 steps.
1 dataset description
20 minutes of generating
60 minutes of fine-tuning on my Macbook Pro

Tutorial: https://nbsanity.com/static/552eb50cbd91bedb4e5b73fddca2664a/fine-tune-modernbert-classifier.html

AI & ML interests

Recent Activity

Team members 243

somosnlp's activity