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

ouhenio updated a Space 17 days ago

somosnlp/mapa-blend-es

lewtun authored a paper about 1 month ago

SmolVLM: Redefining small and efficient multimodal models

pcuenq authored a paper about 1 month ago

SmolVLM: Redefining small and efficient multimodal models

View all activity

somosnlp's activity

davidberenstein1957

posted an update 1 day ago

Post

721

Good answers are not necessarily factual answers: an analysis of hallucination in leading LLMs

https://huggingface.co/blog/davidberenstein1957/phare-analysis-of-hallucination-in-leading-llms

davidberenstein1957

posted an update 15 days ago

Post

2170

🔥 Announcing FLUX-Juiced: The Fastest Image Generation Endpoint (2.6x faster)!

Optimisations are widely applied and can reduce inference time, but their impact on quality often remains unclear, so we decided to challenge the status quo and create our own optimised version of FLUX.1[dev] called FLUX-juiced.

Blog: https://huggingface.co/blog/PrunaAI/flux-fastest-image-generation-endpoint

ouhenio

updated a Space 17 days ago

Mapa Blend-es

🌍

Revisa el avance colectivo de blend-es 😊

davidberenstein1957

posted an update 20 days ago

Post

1701

🧑‍🏫 I wrote a brief blogpost to give An Introduction to AI Model Optimization Techniques!

URL: https://huggingface.co/blog/PrunaAI/introduction-to-ai-model-optimization-techniques

davidberenstein1957

posted an update 22 days ago

Post

1382

RealHarm: A Collection of Real-World Language Model Application Failure

I'm David from Giskard, and we work on securing your Agents.
Today, we are launching RealHarm: a dataset of real-world problematic interactions with AI agents, drawn from publicly reported incidents.

Check out the dataset and paper: https://realharm.giskard.ai/

lewtun

authored a paper about 1 month ago

SmolVLM: Redefining small and efficient multimodal models

Paper • 2504.05299 • Published about 1 month ago • 180

davidberenstein1957

posted an update about 1 month ago

Post

2090

🚨 New Bonus Unit: Tracing & Evaluating Your Agent! 🚨

Learn how to transform your agent from a simple demo into a robust, reliable product ready for real users.

UNIT: https://huggingface.co/learn/agents-course/bonus-unit2/introduction

In this unit, you'll learn:
- Offline Evaluation – Benchmark and iterate your agent using datasets.
- Online Evaluation – Continuously track key metrics such as latency, costs, and user feedback.

Happy testing and improving!

Thanks Langfuse team!

lewtun

authored a paper about 2 months ago

Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning

Paper • 2503.07572 • Published Mar 10 • 44

lewtun

posted an update about 2 months ago

Post

2525

Introducing OlympicCoder: a series of open reasoning models that can solve olympiad-level programming problems 🧑‍💻

- 7B open-r1/OlympicCoder-7B
- 32B open-r1/OlympicCoder-32B

We find that OlympicCoder models outperform Claude 3.7 Sonnet, as well as others over 100x larger 💪

Together with the models, we are releasing:

📊CodeForces-CoTs: new dataset of code problems from the most popular competitive coding platform, with R1 traces in C++ and Python open-r1/codeforces-cots

🏆 IOI'2024: a new benchmark of VERY hard programming problems where even frontier models struggle to match human performance open-r1/ioi

For links to the models and datasets, check out our latest progress report from Open R1: https://huggingface.co/blog/open-r1/update-3

1 reply

davidberenstein1957

posted an update 2 months ago

Post

2416

🔥 Text2SQL, explore and share any data analysis!

🤗 Hugging Face - Dataset Studio is an amazing new feature.

🚀 Start yourself: fka/awesome-chatgpt-prompts

📺 YouTube: https://youtu.be/5LUZq7MHolA?feature=shared

davidberenstein1957

posted an update 2 months ago

Post

4247

🥊 Epic Agent Framework Showdown! Available today!

🔵 In the blue corner, the versatile challenger with a proven track record of knowledge retrieval: LlamaIndex!

🛑 In the red corner, the defender, weighing in with lightweight efficiency: Hugging Face smolagents!

🔗 URL:

agents-course

We just published the LlamaIndex unit for the agents course, and it is set to offer a great contrast between the smolagents unit by looking at

- What makes llama-index stand-out
- How the LlamaHub is used for integrations
- Creating QueryEngine components
- Using agents and tools
- Agentic and multi-agent workflows

The team has been working flat-out on this for a few weeks. Supported by Logan Markewich and Laurie Voss over at LlamaIndex.

Who won? You decide!

davidberenstein1957

posted an update 2 months ago

Post

3042

🫸 New release to push vector search to the Hub with vicinity and work with any serialisable objects.

🧑‍🏫 KNN, HNSW, USEARCH, ANNOY, PYNNDESCENT, FAISS, and VOYAGER.

🔗 Example Repo: minishlab/my-vicinity-repo

davidberenstein1957

posted an update 3 months ago

Post

3311

🚀 Find banger tools for your smolagents!

I created the Tools gallery, which makes tools specifically developed by/for smolagents searchable and visible. This will help with:
- inspiration
- best practices
- finding cool tools

Space: davidberenstein1957/smolagents-and-tools

1 reply

lewtun

posted an update 3 months ago

Post

5203

Introducing OpenR1-Math-220k!

open-r1/OpenR1-Math-220k

The community has been busy distilling DeepSeek-R1 from inference providers, but we decided to have a go at doing it ourselves from scratch 💪

What’s new compared to existing reasoning datasets?

♾ Based on AI-MO/NuminaMath-1.5: we focus on math reasoning traces and generate answers for problems in NuminaMath 1.5, an improved version of the popular NuminaMath-CoT dataset.

🐳 800k R1 reasoning traces: We generate two answers for 400k problems using DeepSeek R1. The filtered dataset contains 220k problems with correct reasoning traces.

📀 512 H100s running locally: Instead of relying on an API, we leverage vLLM and SGLang to run generations locally on our science cluster, generating 180k reasoning traces per day.

⏳ Automated filtering: We apply Math Verify to only retain problems with at least one correct answer. We also leverage Llama3.3-70B-Instruct as a judge to retrieve more correct examples (e.g for cases with malformed answers that can’t be verified with a rules-based parser)

📊 We match the performance of DeepSeek-Distill-Qwen-7B by finetuning Qwen-7B-Math-Instruct on our dataset.

🔎 Read our blog post for all the nitty gritty details: https://huggingface.co/blog/open-r1/update-2

davidberenstein1957

posted an update 3 months ago

Post

2485

Fine-tune Deepseek-R1 with a Synthetic Reasoning Dataset

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

plaguss

authored a paper 3 months ago

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

Paper • 2502.02737 • Published Feb 4 • 229

lewtun

authored a paper 3 months ago

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

Paper • 2502.02737 • Published Feb 4 • 229

gabrielmbmb

authored a paper 3 months ago

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

Paper • 2502.02737 • Published Feb 4 • 229

davidberenstein1957

posted an update 3 months ago

Post

2084

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 3 months ago

Post

2888

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

AI & ML interests

Recent Activity

Team members 281

somosnlp's activity

Mapa Blend-es