12 6 3

Santiago Viquez

santiviquez

https://www.santiviquez.com/

santiviquez

AI & ML interests

ML @ NannyML. A bit of everything. NLP, RL, and, of course, tabular. In the GenAI era, how can you not love tabular data? Educational content and OSS.

Articles

I ran 580 model-dataset experiments to show that, even if you try very hard, it is almost impossible to know that a model is degrading just by looking at data drift results

29 days ago

Are your NLP models deteriorating post-deployment? Let’s use unlabelled data to find out

Nov 16, 2023

Organizations

Posts 21

Post

1027

They: you need ground truth to measure performance! 😠

NannyML: hold my beer...

Post

936

Just published a new article 😊

https://huggingface.co/blog/santiviquez/data-drift-estimate-model-performance

View all posts

Collections 1

spaces 2

Sleeping

💩

Noisy Human

Running

🦀

Ai Act

models 19

Santiago Viquez

AI & ML interests

Articles

I ran 580 model-dataset experiments to show that, even if you try very hard, it is almost impossible to know that a model is degrading just by looking at data drift results

Are your NLP models deteriorating post-deployment? Let’s use unlabelled data to find out

Organizations

Posts 21

Collections 1

Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translation

LLM-Eval: Unified Multi-Dimensional Automatic Evaluation for Open-Domain Conversations with Large Language Models

Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation

BARTScore: Evaluating Generated Text as Text Generation

spaces 2

Noisy Human

Ai Act

models 19

santiviquez/flan-t5-small-ppo

santiviquez/reward_modeling_anthropic_hh

santiviquez/quora-qa-flan-t5-small

santiviquez/t5-small-finetuned-samsum-en

santiviquez/bart-base-finetuned-samsum-en

santiviquez/amazon-reviews-sentiment-bert-base-uncased-6000-samples

santiviquez/amazon-reviews-sentiment-distilbert-base-uncased-6000-samples

santiviquez/amazon-reviews-finetuning-distilbert-base-uncased

santiviquez/amazon-reviews-finetuning-distilbert-base-uncased_books

santiviquez/amazon-reviews-finetuning-bert-base-sentiment

datasets 1

santiviquez/marketing

Santiago Viquez

AI & ML interests

Articles

I ran 580 model-dataset experiments to show that, even if you try very hard, it is almost impossible to know that a model is degrading just by looking at data drift results

Are your NLP models deteriorating post-deployment? Let’s use unlabelled data to find out

Organizations

Posts 21

Collections 1

spaces 2 Sort: Recently updated

Noisy Human

Ai Act

models 19 Sort: Recently updated

datasets 1

spaces 2

models 19