Popular repositories Loading

1. smoothie-qwen smoothie-qwen Public

   A lightweight adjustment tool for smoothing token probabilities in the Qwen models to encourage balanced multilingual generation.

   Python 98 7

2. dnotitia-NIAH dnotitia-NIAH Public

   Enhanced multi-needle retrieval testing framework for evaluating LLM long-context understanding capabilities

   Python 12

3. qllm-infer qllm-infer Public

   A modular framework for evaluating quantization algorithms with reproducible and consistent benchmarks.

   Python 3 2

4. HAN HAN Public

   HAN is a large-scale Korean–English visual-language dataset of Korean cultural heritage: 41k images with rich narrative captions. Built for retrieval, captioning, and cross-lingual VLM research.

   2

5. SparseCache SparseCache Public