-
DistilBERT-SQuAD-MultiHop-QA Public
A lightweight QA system fine-tuned on SQuAD_v2 using DistilBERT, with post-processing for precise answer extraction. Designed for extensibility, supporting multi-hop reasoning and other reasoning m…
MIT License UpdatedJan 30, 2025 -
LoRA-Sentiment-Analysis Public
A sentiment analysis project using Hugging Face transformers and LoRA for efficient model fine-tuning. It includes hyperparameter optimization with Optuna, training on the IMDB dataset, and real-ti…
Jupyter Notebook MIT License UpdatedJan 30, 2025 -
Text preprocessing techniques for NLP, leveraging BERT-based Transformer models and tokenization with PyTorch for token embeddings and sentence-level representations.
Jupyter Notebook MIT License UpdatedJan 30, 2025 -
LLM-engineer-handbook Public
Forked from SylphAI-Inc/LLM-engineer-handbookA curated list of Large Language Model resources, covering model training, serving, fine-tuning, and building LLM applications.
MIT License UpdatedDec 15, 2024 -
pytorch_forward_forward Public
Forked from mpezeshki/pytorch_forward_forwardImplementation of Hinton's forward-forward (FF) algorithm - an alternative to back-propagation
Python MIT License UpdatedSep 6, 2023 -
-
{{ message }}