-
Carnegie Mellon University
- Fremont, CA
- https://www.linkedin.com/in/arushkhare/
Highlights
- Pro
Pinned Loading
-
GRPO-Code-Agent-Fine-Tuning
GRPO-Code-Agent-Fine-Tuning PublicFine-tune Qwen2.5-Coder-7B with GRPO using code-execution feedback as the reward (LoRA, Modal H100, vLLM rollouts).
Python 2
-
PayDrift
PayDrift PublicForked from nhmckinney/TartanHacks-2026-Project
by Arush, Devansh, Nathan
JavaScript
-
Quantization-Accuracy-Size-Tradeoff-Study
Quantization-Accuracy-Size-Tradeoff-Study PublicINT8/INT4 quantization of small fine-tuned code models: accuracy drop vs. size savings on HumanEval (llm-compressor + vLLM on Modal).
Python
-
IHSCubeSat-Mission-Software
IHSCubeSat-Mission-Software PublicForked from GISCubeSat/Image-Processing
These are programs written by the Irvington CubeSat Initiative's Mission Software team for the Pleiades-Orpheus satellite.
Python
-
-
Mouse-Control-Device-for-Motor-Function-Disability
Mouse-Control-Device-for-Motor-Function-Disability PublicThese programs allow people with motor function disabilities to control a computer using head movement and facial gestures.
Python
If the problem persists, check the GitHub status page or contact support.
