-
Hephaestus-CCX Public
Hephaestus-CCX (H-CCX): engineering-grounded CAD-generation benchmark with FEA (CalculiX) evaluation harness — 50 curated cases + 466-case candidate pool
-
qwen-sft-runpod Public
Fine-tune Qwen (and other) models on RunPod GPUs via the TRL training-kit. Registry-driven & extensible. Works in Claude Code and OpenAI Codex.
-
-
training-kit Public
Standalone TRL/FSDP training utilities for Qwen fine-tuning
Python UpdatedJun 12, 2026 -
qwen-training-kit Public
Standalone TRL/FSDP training utilities for Qwen fine-tuning
Python UpdatedJun 12, 2026 -
-
-
sh2-eval Public
Evaluation pipeline for SH^2 (Soohak): a benchmark of 1,141 mathematician-authored math problems spanning olympiad to research-adjacent reasoning.
-
-
-
-
-
-
-
KoSimpleEval Public
Simple evaluation kit for Korean/English benchmarks.
Python UpdatedNov 19, 2025 -
-
-
-
fastcampus_llm_training Public
Code Repository for "LLM 모델 개발부터 4개 프로젝트로 완성하는 도메인 특화 파인튜닝 w.추론"
-
-
-
haerae-evaluation-toolkit Public
Forked from HAE-RAE/haerae-evaluation-toolkitThe most modern LLM evaluation toolkit
Python Apache License 2.0 UpdatedFeb 27, 2025 -
-
-
vllm Public
Forked from vllm-project/vllmA high-throughput and memory-efficient inference and serving engine for LLMs
Python Apache License 2.0 UpdatedJan 15, 2025 -
-
-
-
-
{{ message }}