Pinned Loading

1. KV_Cache-Compression-Benchmark KV_Cache-Compression-Benchmark Public

   KV_Cache Compression Benchmark: SnapKV, L2-NORM, KeyDiff. Qwen 2.5 3b

   Python 4

2. picolm picolm Public

   Forked from RightNow-AI/picolm

   Fork of PicoLM exploring CPU inference optimization in C, including AVX2/FMA Q4_K and Q6_K kernels with ~3× speedup on TinyLlama in my x86 test setup.

   C 2

3. PDLPR-algorithm PDLPR-algorithm Public

   Car Plate Recognition and Reconstruction with Deep Learning

   Jupyter Notebook

4. lightweight-model-for-signal-processing lightweight-model-for-signal-processing Public

   lightweight model for signal processing

   Python

5. Semantic-Museum-Guide-Robot-with-Ambient-Aware-Reasoning Semantic-Museum-Guide-Robot-with-Ambient-Aware-Reasoning Public

   An intelligent museum guide robot built with ROS 2 and TIAGo, combining semantic reasoning, ambient-aware decision making, human-aware navigation, and visitor interaction to provide adaptive and ex…

   Python 1

6. Ancient-to-Modern-Italian-Automatic-Translation Ancient-to-Modern-Italian-Automatic-Translation Public

   Finetuning and evaluating LLMs on Ancient-to-Modern Italian translation task.

   Jupyter Notebook 1