Pinned Repositories
azure-ml-transformers
A collection of recipes in azure ml that use Hugging Face transformers
flash-pix2struct-azureml
hf-notebooks
A collection of various notebooks for atypical transformer usage.
hp_wiki_scrapy
A scrapy project to pull text from the pages of harrypotter.fandom.com to use in a RAG model.
llm-pretraining-azureml
need4speed
Speed tests for language models in pytorch
pii-data-detection
9th place solution to Kaggle Competition: PII Data Detection
strideformer
Using short models to classify long texts
nbroad1881's Repositories
nbroad1881/strideformer
Using short models to classify long texts
nbroad1881/pii-data-detection
9th place solution to Kaggle Competition: PII Data Detection
nbroad1881/need4speed
Speed tests for language models in pytorch
nbroad1881/flash-pix2struct-azureml
nbroad1881/hf-notebooks
A collection of various notebooks for atypical transformer usage.
nbroad1881/llm-pretraining-azureml
nbroad1881/encoder-decoders
Use models like Llama as an encoder-decoder
nbroad1881/serverless-news
Create a serverless lambda function to pull recent news headlines and store them in a database
nbroad1881/azure-ml-transformers
A collection of recipes in azure ml that use Hugging Face transformers
nbroad1881/azureml-fa2-clm
Training a CLM using flash attention 2 in Azure ML
nbroad1881/biomedical
Tools for curating biomedical training data for large-scale language modeling
nbroad1881/fasthtml-hf
Huggingface deployment for FastHTML
nbroad1881/health-fact
Experiments on the health fact dataset
nbroad1881/kaggle-images
Upload images to put on kaggle
nbroad1881/llm-science-exam
6th Position Solution Code for Kaggle - LLM Science Exam Competition
nbroad1881/miniature-potato
nbroad1881/nbme
nbroad1881/nbroad1881
nbroad1881/redesigned-train
nbroad1881/SeeKnowBias
nbroad1881/site
nbroad1881/text-embeddings-inference
A blazing fast inference solution for text embeddings models
nbroad1881/text-generation-inference
Large Language Model Text Generation Inference
nbroad1881/tez
Tez is a super-simple and lightweight Trainer for PyTorch. It also comes with many utils that you can use to tackle over 90% of deep learning projects in PyTorch.
nbroad1881/token-sequence-classification
Use labels as tokens to classify a sequence.
nbroad1881/transformers
🤗Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.
nbroad1881/transformers-notes
Notes with important details about papers, models, libraries related to transformers
nbroad1881/upgraded-meme
nbroad1881/uspppm
Code for the Kaggle competition: U.S. Patent Phrase to Phrase Matching https://www.kaggle.com/competitions/us-patent-phrase-to-phrase-matching
nbroad1881/vision-language
Training vision-language models