Search
Qwen · Fine-tuning
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Fix a GitHub issue on OpenPipe/ART and open a PR. An agent skill from OpenPipe/ART. | OpenPipe/ | 11k | — | ~840 | Automated safety check: Notes | Apache-2.0 | today |
| 2 | 2.Train Rl RL training reference for the ART framework. An agent skill from OpenPipe/ART. | OpenPipe/ | 11k | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | today |
| 3 | SFT training reference for the ART framework. An agent skill from OpenPipe/ART. | OpenPipe/ | 11k | — | ~2.9k | Automated safety check: Pass | Apache-2.0 | today |
| 4 | Rules for adding a new model or model family to the finetuning pipeline, or changing finetuning behavior for an existing one — engine-agnostic customization via family hooks instead of if/else in… | overmind-core/ | 612 | — | ~3.2k | Automated safety check: Pass | AGPL-3.0 | today |
| 5 | Guides reinforcement-learning post-training of LLMs with slime, which pairs Megatron-LM training with SGLang rollouts, including GRPO runs on GLM, Qwen3 and Llama 3 models. | Orchestra-Research/ | 13k | 4 repos | ~2.8k | Automated safety check: Pass | MIT | 3 mo ago |
| 6 | Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). | Orchestra-Research/ | 13k | 2 repos | ~2.8k | Automated safety check: Pass | MIT | 3 mo ago |
| 7 | 7.Qwen21 Qwen-Image-2.1 LoRA line (NOT Anima) — running cache/train through the daemon, make gui-qwen, the CacheRequest/TrainRequest flag surface and how to add a field, model-dir resolution, cache layout… | sorryhyun/ | 125 | — | ~1.9k | Automated safety check: Notes | MIT | today |
| 8 | Calculate training costs for Tinker fine-tuning jobs. An agent skill from sundial-org/skills. | sundial-org/ | 153 | — | ~1.2k | Automated safety check: Pass | No licence | 2 mo ago |
| 9 | Fine-tune LLMs with LlamaFactory — register datasets, train via YAML configs, merge LoRA adapters and serve the result. | Prism-Shadow/ | 2.5k | — | ~855 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 10 | Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA. | sickn33/ | 47k | 1 repo | ~8.3k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 11 | Train a custom anime LoRA on the ANIMA base model with Citron's local Gradio trainer (kohya sd-scripts), <6GB VRAM, character/style LoRAs; covers setup, dataset prep, training params, and using the… | artokun/ | 803 | — | ~2.2k | Automated safety check: Pass | MIT | 6 days ago |
| 12 | 12.Ernie Image Build Baidu ERNIE-Image / ERNIE-Image-Turbo workflows, primarily TEXT-TO-IMAGE. | artokun/ | 803 | — | ~4.5k | Automated safety check: Pass | MIT | 6 days ago |
| 13 | 13.Flux Txt2img Build Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patterns | artokun/ | 803 | — | ~3k | Automated safety check: Pass | MIT | 6 days ago |
| 14 | Curated download URLs and target directories, organized by family (Flux, WAN, LTX, Qwen, Z-Image, SD15/SDXL), for every model the comfyui-mcp skills reference, covering checkpoints, VAEs, text… | artokun/ | 803 | — | ~2.1k | Automated safety check: Pass | MIT | 6 days ago |
| 15 | Build Qwen Image Edit workflows covering model loading, conditioning, LoRAs, prompt patterns, and XY plot testing | artokun/ | 803 | — | ~4.6k | Automated safety check: Pass | MIT | 6 days ago |
| 16 | 16.Qwen Txt2img Build Qwen Image 2512 text-to-image workflows with QwenImageIntegratedKSampler, separate component loading, lightning LoRAs, and fine-tuned model variants | artokun/ | 803 | — | ~3.3k | Automated safety check: Pass | MIT | 6 days ago |
| 17 | Build Z-Image txt2img workflows. An agent skill from artokun/comfyui-mcp. | artokun/ | 803 | — | ~2.8k | Automated safety check: Pass | MIT | 6 days ago |
| 18 | Expert prompt engineering for FLUX.2 [klein] image generation and editing model. | AnastasiyaW/ | 154 | — | ~2.8k | Automated safety check: Pass | MIT | yesterday |
| 19 | Plan or review LoRA and edit-training work specifically for FLUX.2 Klein or Qwen-Image-Edit, including paired datasets, trainer-version contracts, and held-out fidelity checks. | AnastasiyaW/ | 154 | — | ~4.5k | Automated safety check: Pass | MIT | yesterday |
| 20 | Shared Cosmos3 frontend that explicitly routes Cosmos Framework and Cosmos-RL, validates runtime model/video-dataset/SLURM inputs, consumes an SQSH or packaged backend image, optionally plans… | NVIDIA/ | 3.6k | — | ~5k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 21 | Практическая инженерия диффузионных моделей: архитектуры, обучение, инференс, оптимизация памяти. | AnastasiyaW/ | 154 | — | ~1.2k | Automated safety check: Pass | MIT | yesterday |
| 22 | Verl 分布式训练服务一键拉起与配置。触发场景：(1) 用户要启动 Verl 训练任务或部署 RLHF/DAPO 训练环境 (2) 在 NPU 集群上拉起 Verl 训练容器 (3) 配置 Ray 集群和 SwanLab 监控 (4) 根据 7 位二进制掩码灵活配置加速特性。支持 Qwen3-8B 等 Megatron 模型的 DAPO 训练全流程。 | ascend-ai-coding/ | 174 | — | ~2k | Automated safety check: Pass | No licence | yesterday |
| 23 | Universal VLM (vision-language understanding model) training guide for Huawei Ascend NPU using MindSpeed-MM. | ascend-ai-coding/ | 174 | — | ~5.2k | Automated safety check: Pass | No licence | yesterday |
