I Hackathon Somos NLP: PLN en Español

non-profit

AI & ML interests

Hackathon de PLN en español open-source y enfocado a los Objetivos de Desarrollo Sostenible de la ONU. Organizado por Somos NLP y patrocinado por Platzi, Paperspace y Hugging Face.

Recent Activity

DrishtiSharma authored a paper about 2 months ago

1-800-SHARED-TASKS at RegNLP: Lexical Reranking of Semantic Retrieval (LeSeR) for Regulatory Question Answering

DrishtiSharma authored a paper about 2 months ago

Maya: An Instruction Finetuned Multilingual Multimodal Model

DrishtiSharma authored a paper about 2 months ago

INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge

View all activity

somosnlp-hackathon-2022's activity

haritzpuerto

posted an update 2 days ago

Post

498

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 3 days ago

Post

1405

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

DrishtiSharma

authored 5 papers about 2 months ago

1-800-SHARED-TASKS at RegNLP: Lexical Reranking of Semantic Retrieval (LeSeR) for Regulatory Question Answering

Paper • 2412.06009 • Published Dec 8, 2024

Maya: An Instruction Finetuned Multilingual Multimodal Model

Paper • 2412.07112 • Published Dec 10, 2024 • 27

INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge

Paper • 2411.19799 • Published Nov 29, 2024 • 11

SeQwen at the Financial Misinformation Detection Challenge Task: Sequential Learning for Claim Verification and Explanation Generation in Financial Domains

Paper • 2412.00549 • Published Nov 30, 2024 • 1

1-800-SHARED-TASKS @ NLU of Devanagari Script Languages: Detection of Language, Hate Speech, and Targets using LLMs

Paper • 2411.06850 • Published Nov 11, 2024 • 4

haritzpuerto

authored a paper 3 months ago

Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models

Paper • 2411.00154 • Published Oct 31, 2024

DrishtiSharma

authored a paper 3 months ago

M-RewardBench: Evaluating Reward Models in Multilingual Settings

Paper • 2410.15522 • Published Oct 20, 2024 • 11

mariagrandury

authored a paper 4 months ago

Evaluating Large Language Models with Tests of Spanish as a Foreign Language: Pass or Fail?

Paper • 2409.15334 • Published Sep 8, 2024 • 1

rockdrigoma

updated a Space 6 months ago

Running

🌽

Spanish to Nahuatl Translation

mariagrandury

authored a paper 6 months ago

The #Somos600M Project: Generating NLP resources that represent the diversity of the languages from LATAM, the Caribbean, and Spain

Paper • 2407.17479 • Published Jul 1, 2024 • 1

haritzpuerto

authored a paper 7 months ago

Fine-Tuning with Divergent Chains of Thought Boosts Reasoning Through Self-Correction in Language Models

Paper • 2407.03181 • Published Jul 3, 2024 • 1

mrm8488

posted an update 7 months ago

Post

4977

🚨Exciting news for the Multilingual Synthetic Data Community!🚨

I’ve taken inspiration from the MAGPIE paper on Llama-3-8B-instruct and extended its capabilities. Here’s what’s new!

🗞 The MAGPIE paper showcased that if you use the instruction-tuned version (Llama-3-8B-instruct) to generate synthetic instructions and then fine-tune the base version (Llama-3-8B) on this dataset, you can improve even the it-tuned version

🤔 While reading a script by Sebastian Raschka, PhD, I wondered: Could these advancements be replicated in other languages? Specifically, could they benefit non-English datasets?

🎉 And the answer is YES! At least for Spanish. I've successfully adapted the techniques for Spanish, proving the model's flexibility and multilingual capabilities.

👩‍💻 To make this accessible, I created a basic script (heavily inspired by the Sebastian Raschka one) that allows you to generate similar datasets using ollama models (initially phi and llama3) automatically and upload it to the Hugging Face Hub!
[Script](https://gist.github.com/mrm8488/4650a5e3cc45523798a527a3446eb312)

🔍 Explore the datasets 📚 generated using our new script!

- [Llama-3-8B](https://huggingface.co/datasets/mrm8488/dataset_llama3_5000_samples_es_4231_filtered)
- [Phi-3-medium](https://huggingface.co/datasets/mrm8488/dataset_phi3-medium_5000_samples_es_3906_filtered)
- [Phi-3-mini](https://huggingface.co/datasets/mrm8488/dataset_phi3_5000_samples_es_3282_filtered)

Note: These datasets have basic filtering. Apply additional quality filters before using them to fine-tune large language models.

Inspiration and base script:
https://github.com/rasbt/LLMs-from-scratch/blob/main/ch07/05_dataset-generation/llama3-ollama.ipynb
https://www.linkedin.com/feed/update/urn:li:activity:7210982019751661568/