Pinned Repositories
bigcode-evaluation-harness
A framework for the evaluation of autoregressive code generation language models.
Bespoke_LLMs_TALK
Slides and code for Bespoke LLMs : Adapting OSS LLMs for your use case.
Colab_Transformers
Colab notebooks and code used for training and inferencing BERT and other transformer models from pytorch transformers
FastTokenizersWrapper
A wrapper for Huggingface's Tokenizers library , for it to be used along with existing version of Huggingface Transformers library.
Interpretable-NLP-Talk
Hack Session on Interpreting NLP models at DataHack Summit 2019.
language-detection-fasttext
Sample code illustrating FastText's pre-trained language Identification model usage
Multilabel-Transformers
A repository to finetune transformers on a multilabel classification task ( based on transformers library ).
mutate
A library to synthesize text datasets using Large Language Models (LLM)
NLP_paper_notes
My Notes and observations of Interesting NLP papers. My interests are representation learning, Metric learning and Information retrieval
medhalt
infinitylogesh's Repositories
infinitylogesh/mutate
A library to synthesize text datasets using Large Language Models (LLM)
infinitylogesh/language-detection-fasttext
Sample code illustrating FastText's pre-trained language Identification model usage
infinitylogesh/Bespoke_LLMs_TALK
Slides and code for Bespoke LLMs : Adapting OSS LLMs for your use case.
infinitylogesh/Interpretable-NLP-Talk
Hack Session on Interpreting NLP models at DataHack Summit 2019.
infinitylogesh/Colab_Transformers
Colab notebooks and code used for training and inferencing BERT and other transformer models from pytorch transformers
infinitylogesh/NLP_paper_notes
My Notes and observations of Interesting NLP papers. My interests are representation learning, Metric learning and Information retrieval
infinitylogesh/Multilabel-Transformers
A repository to finetune transformers on a multilabel classification task ( based on transformers library ).
infinitylogesh/FastTokenizersWrapper
A wrapper for Huggingface's Tokenizers library , for it to be used along with existing version of Huggingface Transformers library.
infinitylogesh/ABSA-BERT-QA
Aspect based sentiment analysis as QA problem
infinitylogesh/bigcode-evaluation-harness
A framework for the evaluation of autoregressive code generation language models.
infinitylogesh/code-eval
Run evaluation on LLMs using human-eval benchmark
infinitylogesh/dolly
infinitylogesh/flax-sentence-embeddings
Shared code for training sentence embeddings with Flax / JAX
infinitylogesh/How-to-do-more-with-less-data
Blog posts and demo on using Active learning to achieve good ML performance with less data
infinitylogesh/incoder
Generative model for code infilling and synthesis
infinitylogesh/infinitylogesh.github.io
My Blog
infinitylogesh/keras-scaffolding
A scaffolding for keras and tensorflow with some callbacks , metrics and logs inbuilt.
infinitylogesh/medmcqa.github.io
infinitylogesh/MicroLMs
Implementation of common LM architectures and training Micro LMs of the arch.
infinitylogesh/open-interpreter
A natural language interface for computers
infinitylogesh/probability_simulations
Simulations of probability problems and concepts
infinitylogesh/SA-Sent
Implementation for SA-LSTM
infinitylogesh/santacoder-finetuning
Fine-tune SantaCoder for Code/Text Generation.
infinitylogesh/se-pytorch-xla
infinitylogesh/sentence-transformers
Sentence Embeddings with BERT & XLNet
infinitylogesh/Speculative-Sampling
Implementation of Speculative Sampling as described in "Accelerating Large Language Model Decoding with Speculative Sampling" by Deepmind
infinitylogesh/TensorRT-LLM
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
infinitylogesh/twint
An advanced Twitter scraping & OSINT tool written in Python that doesn't use Twitter's API, allowing you to scrape a user's followers, following, Tweets and more while evading most API limitations.
infinitylogesh/Wizcoder_benchmark
infinitylogesh/xformers
Hackable and optimized Transformers building blocks, supporting a composable construction.