HITgram: A Platform for Experimenting with n-gram Language Models
This provides a practical tool for resource-constrained environments, though it is incremental as it builds on existing n-gram techniques.
The paper tackles the problem of resource-intensive large language models by introducing HITgram, a lightweight platform for n-gram model experimentation, which achieves 50,000 tokens/second and constructs 4-grams from a 1GB file in under 298 seconds on an 8 GB RAM system.
Large language models (LLMs) are powerful but resource intensive, limiting accessibility. HITgram addresses this gap by offering a lightweight platform for n-gram model experimentation, ideal for resource-constrained environments. It supports unigrams to 4-grams and incorporates features like context sensitive weighting, Laplace smoothing, and dynamic corpus management to e-hance prediction accuracy, even for unseen word sequences. Experiments demonstrate HITgram's efficiency, achieving 50,000 tokens/second and generating 2-grams from a 320MB corpus in 62 seconds. HITgram scales efficiently, constructing 4-grams from a 1GB file in under 298 seconds on an 8 GB RAM system. Planned enhancements include multilingual support, advanced smoothing, parallel processing, and model saving, further broadening its utility.