{ "recipes": [ { "kind": "run", "task": "Classification", "script": "classification/classify-dataset-sglang.py", "repo": "uv-scripts/classification", "page": "https://huggingface.co/datasets/uv-scripts/classification/blob/main/classify-dataset-sglang.py", "url": "https://huggingface.co/datasets/uv-scripts/classification/raw/main/classify-dataset-sglang.py", "models": [ "HuggingFaceTB/SmolLM3-3B" ], "support": null, "source": "header", "flavor": "l4x1", "timeout": "1h", "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/classification/raw/main/classify-dataset-sglang.py \\\n --input-dataset your-username/emails \\\n --column content \\\n --labels \"spam,ham\" \\\n --output-dataset your-username/emails-classified \\\n --reasoning", "summary": "Classify text columns in Hugging Face datasets using SGLang with reasoning-aware models.", "declared": true }, { "kind": "run", "task": "Classification", "script": "classification/classify-dataset.py", "repo": "uv-scripts/classification", "page": "https://huggingface.co/datasets/uv-scripts/classification/blob/main/classify-dataset.py", "url": "https://huggingface.co/datasets/uv-scripts/classification/raw/main/classify-dataset.py", "models": [ "HuggingFaceTB/SmolLM3-3B" ], "support": null, "source": "header", "flavor": "l4x1", "timeout": "1h", "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/classification/raw/main/classify-dataset.py \\\n --input-dataset your-username/emails \\\n --column content \\\n --labels \"spam,ham\" \\\n --output-dataset your-username/emails-classified \\\n --enable-reasoning", "summary": "Classify text columns in Hugging Face datasets using vLLM with structured outputs.", "declared": true }, { "kind": "run", "task": "Classification", "script": "classification/classify-gliner2.py", "repo": "uv-scripts/classification", "page": "https://huggingface.co/datasets/uv-scripts/classification/blob/main/classify-gliner2.py", "url": "https://huggingface.co/datasets/uv-scripts/classification/raw/main/classify-gliner2.py", "models": [ "fastino/gliner2.5-multi-v1" ], "support": null, "source": "header", "flavor": "t4-small", "timeout": "1h", "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/classification/raw/main/classify-gliner2.py \\\n fancyzhx/ag_news your-username/ag-news-gliner2 \\\n --labels World Sports Business \"Science and technology\" --max-samples 1000", "summary": "Classify a text column of a Hub dataset with GLiNER2 — zero-shot, or with your fine-tuned model.", "declared": true }, { "kind": "train", "task": "Fine-tuning", "script": "classification/train-classifier.py", "repo": "uv-scripts/classification", "page": "https://huggingface.co/datasets/uv-scripts/classification/blob/main/train-classifier.py", "url": "https://huggingface.co/datasets/uv-scripts/classification/raw/main/train-classifier.py", "models": [ "LiquidAI/LFM2.5-Encoder-350M" ], "support": null, "source": "header", "flavor": "l4x1", "timeout": "1h", "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/classification/raw/main/train-classifier.py \\\n fancyzhx/ag_news your-username/my-news-classifier \\\n --max-samples 2000 --epochs 1", "summary": "Fine-tune a text-classification encoder on a Hub dataset and push the trained model to the Hub.", "declared": false }, { "kind": "train", "task": "Fine-tuning", "script": "classification/train-gliner2.py", "repo": "uv-scripts/classification", "page": "https://huggingface.co/datasets/uv-scripts/classification/blob/main/train-gliner2.py", "url": "https://huggingface.co/datasets/uv-scripts/classification/raw/main/train-gliner2.py", "models": [ "fastino/gliner2.5-multi-v1" ], "support": null, "source": "header", "flavor": "t4-small", "timeout": "1h", "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/classification/raw/main/train-gliner2.py \\\n biglam/blbooksgenre your-username/gliner2-blbooks-genre \\\n --dataset-config title_genre_classifiction --text-column title", "summary": "Fine-tune GLiNER2 into a text classifier — a small model (74M to 287M parameters, depending on the base checkpoint) that already works zero-shot.", "declared": false }, { "kind": "train", "task": "Fine-tuning", "script": "classification/train-setfit.py", "repo": "uv-scripts/classification", "page": "https://huggingface.co/datasets/uv-scripts/classification/blob/main/train-setfit.py", "url": "https://huggingface.co/datasets/uv-scripts/classification/raw/main/train-setfit.py", "models": [ "sentence-transformers/all-MiniLM-L6-v2" ], "support": null, "source": "documented", "flavor": null, "timeout": null, "command": "hf jobs uv run --flavor cpu-basic --secrets HF_TOKEN \\\n https://huggingface.co/datasets/uv-scripts/classification/raw/main/train-setfit.py \\\n fancyzhx/ag_news your-username/ag-news-setfit \\\n --num-samples 8", "summary": "Few-shot text classification with SetFit — train on 8-64 labelled examples per class, on CPU or GPU.", "declared": false }, { "kind": "run", "task": "Embeddings", "script": "embeddings/embed-to-lance.py", "repo": "uv-scripts/embeddings", "page": "https://huggingface.co/datasets/uv-scripts/embeddings/blob/main/embed-to-lance.py", "url": "https://huggingface.co/datasets/uv-scripts/embeddings/raw/main/embed-to-lance.py", "models": [ "BAAI/bge-base-en-v1.5" ], "support": null, "source": "documented", "flavor": null, "timeout": null, "command": "hf jobs uv run --flavor l4x1 -s HF_TOKEN \\\n https://huggingface.co/datasets/uv-scripts/embeddings/raw/main/embed-to-lance.py \\\n stanfordnlp/imdb your-username/imdb-vecdb --column text --model BAAI/bge-base-en-v1.5 --private", "summary": "Embed a Hugging Face dataset and push it back as a Lance vector index — a Hub dataset that IS a searchable vector database.", "declared": false }, { "kind": "run", "task": "Embeddings", "script": "embeddings/generate-embeddings-vllm.py", "repo": "uv-scripts/embeddings", "page": "https://huggingface.co/datasets/uv-scripts/embeddings/blob/main/generate-embeddings-vllm.py", "url": "https://huggingface.co/datasets/uv-scripts/embeddings/raw/main/generate-embeddings-vllm.py", "models": [ "Qwen/Qwen3-Embedding-0.6B" ], "support": null, "source": "documented", "flavor": null, "timeout": null, "command": "hf jobs uv run --flavor l4x1 -s HF_TOKEN \\\n https://huggingface.co/datasets/uv-scripts/embeddings/raw/main/generate-embeddings-vllm.py \\\n stanfordnlp/imdb your-username/imdb-embeddings --column text --model Qwen/Qwen3-Embedding-0.6B --private", "summary": "High-throughput embedding generation with vLLM pooling mode — the \"scale\" variant of generate-embeddings.py, for large decoder embedding models (e.g.", "declared": false }, { "kind": "run", "task": "Embeddings", "script": "embeddings/generate-embeddings.py", "repo": "uv-scripts/embeddings", "page": "https://huggingface.co/datasets/uv-scripts/embeddings/blob/main/generate-embeddings.py", "url": "https://huggingface.co/datasets/uv-scripts/embeddings/raw/main/generate-embeddings.py", "models": [ "sentence-transformers/all-MiniLM-L6-v2" ], "support": null, "source": "documented", "flavor": null, "timeout": null, "command": "hf jobs uv run --flavor l4x1 -s HF_TOKEN \\\n https://huggingface.co/datasets/uv-scripts/embeddings/raw/main/generate-embeddings.py \\\n stanfordnlp/imdb your-username/imdb-embeddings \\\n --column text --model sentence-transformers/all-MiniLM-L6-v2", "summary": "Generate embeddings for a Hugging Face dataset (text OR images) with sentence-transformers, and push the result back to the Hub as a new dataset with…", "declared": true }, { "kind": "run", "task": "Embeddings", "script": "embeddings/launch-embedding-fleet.py", "repo": "uv-scripts/embeddings", "page": "https://huggingface.co/datasets/uv-scripts/embeddings/blob/main/launch-embedding-fleet.py", "url": "https://huggingface.co/datasets/uv-scripts/embeddings/raw/main/launch-embedding-fleet.py", "models": [ "sentence-transformers/all-MiniLM-L6-v2" ], "support": null, "source": "flags-needed", "flavor": null, "timeout": null, "command": null, "summary": "Fan one embedding run out across N Hugging Face Jobs, then consolidate.", "declared": false }, { "kind": "run", "task": "Entities", "script": "gliner/extract-entities.py", "repo": "uv-scripts/gliner", "page": "https://huggingface.co/datasets/uv-scripts/gliner/blob/main/extract-entities.py", "url": "https://huggingface.co/datasets/uv-scripts/gliner/raw/main/extract-entities.py", "models": [ "urchade/gliner_multi-v2.1" ], "support": null, "source": "documented", "flavor": null, "timeout": null, "command": "hf jobs uv run --flavor t4-small \\\n --secrets HF_TOKEN \\\n https://huggingface.co/datasets/uv-scripts/gliner/raw/main/extract-entities.py \\\n librarian-bots/model_cards_with_metadata \\\n your-username/model-cards-entities \\\n --text-column card \\\n --entity-types Person Organization Dataset Model Framework \\\n --max-samples 5000", "summary": "Extract named entities from a text column of a HuggingFace dataset using GLiNER.", "declared": true }, { "kind": "run", "task": "OCR", "script": "ocr/deepseek-ocr-vllm.py", "repo": "uv-scripts/ocr", "page": "https://huggingface.co/datasets/uv-scripts/ocr/blob/main/deepseek-ocr-vllm.py", "url": "https://huggingface.co/datasets/uv-scripts/ocr/raw/main/deepseek-ocr-vllm.py", "models": [ "deepseek-ai/DeepSeek-OCR" ], "support": "core", "source": "header", "flavor": "a10g-small", "timeout": null, "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/ocr/raw/main/deepseek-ocr-vllm.py \\\n my-dataset my-output --max-samples 10", "summary": "Convert document images to markdown using DeepSeek-OCR with vLLM.", "declared": true }, { "kind": "run", "task": "OCR", "script": "ocr/deepseek-ocr2-vllm.py", "repo": "uv-scripts/ocr", "page": "https://huggingface.co/datasets/uv-scripts/ocr/blob/main/deepseek-ocr2-vllm.py", "url": "https://huggingface.co/datasets/uv-scripts/ocr/raw/main/deepseek-ocr2-vllm.py", "models": [ "deepseek-ai/DeepSeek-OCR-2" ], "support": "core", "source": "header", "flavor": "a10g-small", "timeout": null, "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/ocr/raw/main/deepseek-ocr2-vllm.py \\\n my-dataset my-output --max-samples 10", "summary": "Convert document images to markdown using DeepSeek-OCR-2 with vLLM.", "declared": true }, { "kind": "run", "task": "OCR", "script": "ocr/dots-mocr.py", "repo": "uv-scripts/ocr", "page": "https://huggingface.co/datasets/uv-scripts/ocr/blob/main/dots-mocr.py", "url": "https://huggingface.co/datasets/uv-scripts/ocr/raw/main/dots-mocr.py", "models": [ "rednote-hilab/dots.mocr" ], "support": "core", "source": "header", "flavor": "a10g-small", "timeout": null, "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/ocr/raw/main/dots-mocr.py \\\n INPUT_DATASET OUTPUT_DATASET", "summary": "Convert document images to markdown using dots.mocr with vLLM.", "declared": true }, { "kind": "run", "task": "OCR", "script": "ocr/dots-ocr.py", "repo": "uv-scripts/ocr", "page": "https://huggingface.co/datasets/uv-scripts/ocr/blob/main/dots-ocr.py", "url": "https://huggingface.co/datasets/uv-scripts/ocr/raw/main/dots-ocr.py", "models": [ "rednote-hilab/dots.ocr" ], "support": "core", "source": "header", "flavor": "a10g-small", "timeout": null, "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/ocr/raw/main/dots-ocr.py \\\n INPUT_DATASET OUTPUT_DATASET", "summary": "Convert document images to markdown using DoTS.ocr with vLLM.", "declared": true }, { "kind": "run", "task": "OCR", "script": "ocr/glm-ocr.py", "repo": "uv-scripts/ocr", "page": "https://huggingface.co/datasets/uv-scripts/ocr/blob/main/glm-ocr.py", "url": "https://huggingface.co/datasets/uv-scripts/ocr/raw/main/glm-ocr.py", "models": [ "zai-org/GLM-OCR" ], "support": "core", "source": "header", "flavor": "a10g-small", "timeout": null, "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/ocr/raw/main/glm-ocr.py \\\n {source_dataset} \\\n \\\n --image-column {image_column} \\\n --batch-size {batch_size} \\\n --task {task}", "summary": "Convert document images to markdown using GLM-OCR with vLLM.", "declared": true }, { "kind": "run", "task": "OCR", "script": "ocr/hunyuan-ocr-1.5.py", "repo": "uv-scripts/ocr", "page": "https://huggingface.co/datasets/uv-scripts/ocr/blob/main/hunyuan-ocr-1.5.py", "url": "https://huggingface.co/datasets/uv-scripts/ocr/raw/main/hunyuan-ocr-1.5.py", "models": [ "tencent/HunyuanOCR" ], "support": "core", "source": "header", "flavor": "a10g-small", "timeout": null, "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/ocr/raw/main/hunyuan-ocr-1.5.py \\\n INPUT_DATASET OUTPUT_DATASET", "summary": "Convert document images to markdown using HunyuanOCR-1.5 with vLLM.", "declared": true }, { "kind": "run", "task": "OCR", "script": "ocr/lift-extract.py", "repo": "uv-scripts/ocr", "page": "https://huggingface.co/datasets/uv-scripts/ocr/blob/main/lift-extract.py", "url": "https://huggingface.co/datasets/uv-scripts/ocr/raw/main/lift-extract.py", "models": [ "datalab-to/lift" ], "support": "core", "source": "header", "flavor": "a100-large", "timeout": null, "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/ocr/raw/main/lift-extract.py \\\n INPUT_DATASET OUTPUT_DATASET \\\n --schema '{\"type\":\"object\",\"properties\":{\"title\":{\"type\":\"string\"}}}' \\\n --max-samples 5 --shuffle --seed 42", "summary": "Extract structured JSON from document images OR multi-page PDFs using Datalab's lift model (datalab-to/lift, 9B, Qwen3.5-based).", "declared": true }, { "kind": "run", "task": "OCR", "script": "ocr/lighton-ocr2-saturate.py", "repo": "uv-scripts/ocr", "page": "https://huggingface.co/datasets/uv-scripts/ocr/blob/main/lighton-ocr2-saturate.py", "url": "https://huggingface.co/datasets/uv-scripts/ocr/raw/main/lighton-ocr2-saturate.py", "models": [ "lightonai/LightOnOCR-2-1B" ], "support": "core", "source": "header", "flavor": "a10g-small", "timeout": "4h", "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/ocr/raw/main/lighton-ocr2-saturate.py \\\n ", "summary": "Convert document images to markdown using LightOnOCR-2 via saturate.", "declared": true }, { "kind": "run", "task": "OCR", "script": "ocr/lighton-ocr2.py", "repo": "uv-scripts/ocr", "page": "https://huggingface.co/datasets/uv-scripts/ocr/blob/main/lighton-ocr2.py", "url": "https://huggingface.co/datasets/uv-scripts/ocr/raw/main/lighton-ocr2.py", "models": [ "lightonai/LightOnOCR-2-1B" ], "support": "core", "source": "header", "flavor": "a10g-small", "timeout": "1h", "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/ocr/raw/main/lighton-ocr2.py \\\n ", "summary": "Convert document images to markdown using LightOnOCR-2 with vLLM.", "declared": true }, { "kind": "run", "task": "OCR", "script": "ocr/lighton-ocr3-bucket.py", "repo": "uv-scripts/ocr", "page": "https://huggingface.co/datasets/uv-scripts/ocr/blob/main/lighton-ocr3-bucket.py", "url": "https://huggingface.co/datasets/uv-scripts/ocr/raw/main/lighton-ocr3-bucket.py", "models": [ "lightonai/LightOnOCR-3-4B" ], "support": "core", "source": "header", "flavor": "a10g-small", "timeout": null, "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/ocr/raw/main/lighton-ocr3-bucket.py \\\n hf://buckets/biglam/britannica/source/pages/00070476bsb \\\n hf://buckets/your-username/ocr-output/britannica --mode grounding --max-samples 20", "summary": "OCR images and PDFs from an HF Bucket (or a directory) using LightOnOCR-3, writing markdown files.", "declared": true }, { "kind": "run", "task": "OCR", "script": "ocr/lighton-ocr3.py", "repo": "uv-scripts/ocr", "page": "https://huggingface.co/datasets/uv-scripts/ocr/blob/main/lighton-ocr3.py", "url": "https://huggingface.co/datasets/uv-scripts/ocr/raw/main/lighton-ocr3.py", "models": [ "lightonai/LightOnOCR-3-4B" ], "support": "core", "source": "header", "flavor": "a10g-small", "timeout": null, "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/ocr/raw/main/lighton-ocr3.py \\\n INPUT_DATASET OUTPUT_DATASET --max-samples 10", "summary": "Convert document images to markdown (or layout blocks) using LightOnOCR-3 with vLLM.", "declared": true }, { "kind": "run", "task": "OCR", "script": "ocr/minicpm-ocr.py", "repo": "uv-scripts/ocr", "page": "https://huggingface.co/datasets/uv-scripts/ocr/blob/main/minicpm-ocr.py", "url": "https://huggingface.co/datasets/uv-scripts/ocr/raw/main/minicpm-ocr.py", "models": [ "openbmb/MiniCPM-OCR-1.0" ], "support": "experimental", "source": "header", "flavor": "a10g-large", "timeout": "2h", "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/ocr/raw/main/minicpm-ocr.py \\\n INPUT_DATASET OUTPUT_DATASET --max-samples 20", "summary": "Convert document images to markdown with OpenBMB's MiniCPM-OCR 1.0 pipeline.", "declared": false }, { "kind": "run", "task": "OCR", "script": "ocr/nuextract3.py", "repo": "uv-scripts/ocr", "page": "https://huggingface.co/datasets/uv-scripts/ocr/blob/main/nuextract3.py", "url": "https://huggingface.co/datasets/uv-scripts/ocr/raw/main/nuextract3.py", "models": [ "numind/NuExtract3" ], "support": "core", "source": "header", "flavor": "a10g-small", "timeout": null, "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/ocr/raw/main/nuextract3.py \\\n INPUT_DATASET OUTPUT_DATASET --max-samples 5 --shuffle --seed 42", "summary": "Convert document images to markdown OR extract structured JSON using NuExtract3 with vLLM.", "declared": true }, { "kind": "run", "task": "OCR", "script": "ocr/olmocr2-vllm.py", "repo": "uv-scripts/ocr", "page": "https://huggingface.co/datasets/uv-scripts/ocr/blob/main/olmocr2-vllm.py", "url": "https://huggingface.co/datasets/uv-scripts/ocr/raw/main/olmocr2-vllm.py", "models": [ "allenai/olmOCR-2-7B-1025-FP8" ], "support": "core", "source": "header", "flavor": "a10g-small", "timeout": "2h", "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/ocr/raw/main/olmocr2-vllm.py \\\n INPUT_DATASET OUTPUT_DATASET", "summary": "Convert document images to markdown using olmOCR-2 with vLLM.", "declared": true }, { "kind": "run", "task": "OCR", "script": "ocr/ovis-ocr2-saturate.py", "repo": "uv-scripts/ocr", "page": "https://huggingface.co/datasets/uv-scripts/ocr/blob/main/ovis-ocr2-saturate.py", "url": "https://huggingface.co/datasets/uv-scripts/ocr/raw/main/ovis-ocr2-saturate.py", "models": [ "ATH-MaaS/OvisOCR2" ], "support": "core", "source": "header", "flavor": "a10g-small", "timeout": "4h", "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/ocr/raw/main/ovis-ocr2-saturate.py \\\n ", "summary": "Convert document images to markdown using OvisOCR2 via saturate.", "declared": true }, { "kind": "run", "task": "OCR", "script": "ocr/ovis-ocr2.py", "repo": "uv-scripts/ocr", "page": "https://huggingface.co/datasets/uv-scripts/ocr/blob/main/ovis-ocr2.py", "url": "https://huggingface.co/datasets/uv-scripts/ocr/raw/main/ovis-ocr2.py", "models": [ "ATH-MaaS/OvisOCR2" ], "support": "core", "source": "header", "flavor": "a10g-small", "timeout": null, "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/ocr/raw/main/ovis-ocr2.py \\\n INPUT_DATASET OUTPUT_DATASET --batch-size 16", "summary": "Convert document images to markdown using OvisOCR2 with vLLM.", "declared": true }, { "kind": "run", "task": "OCR", "script": "ocr/paddleocr-vl-1.6.py", "repo": "uv-scripts/ocr", "page": "https://huggingface.co/datasets/uv-scripts/ocr/blob/main/paddleocr-vl-1.6.py", "url": "https://huggingface.co/datasets/uv-scripts/ocr/raw/main/paddleocr-vl-1.6.py", "models": [ "PaddlePaddle/PaddleOCR-VL-1.6" ], "support": "core", "source": "header", "flavor": "a10g-small", "timeout": null, "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/ocr/raw/main/paddleocr-vl-1.6.py \\\n INPUT_DATASET OUTPUT_DATASET", "summary": "Convert document images to text/tables/formulas using PaddleOCR-VL-1.6 with vLLM.", "declared": true }, { "kind": "run", "task": "OCR", "script": "ocr/qianfan-ocr.py", "repo": "uv-scripts/ocr", "page": "https://huggingface.co/datasets/uv-scripts/ocr/blob/main/qianfan-ocr.py", "url": "https://huggingface.co/datasets/uv-scripts/ocr/raw/main/qianfan-ocr.py", "models": [ "baidu/Qianfan-OCR" ], "support": "core", "source": "header", "flavor": "a10g-small", "timeout": null, "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/ocr/raw/main/qianfan-ocr.py \\\n INPUT_DATASET OUTPUT_DATASET --max-samples 10", "summary": "Convert document images to markdown using Qianfan-OCR with vLLM.", "declared": true }, { "kind": "run", "task": "OCR", "script": "ocr/surya-ocr.py", "repo": "uv-scripts/ocr", "page": "https://huggingface.co/datasets/uv-scripts/ocr/blob/main/surya-ocr.py", "url": "https://huggingface.co/datasets/uv-scripts/ocr/raw/main/surya-ocr.py", "models": [ "datalab-to/surya-ocr-2" ], "support": "core", "source": "header", "flavor": "a10g-small", "timeout": null, "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/ocr/raw/main/surya-ocr.py \\\n INPUT_DATASET OUTPUT_DATASET \\\n --max-samples 5 --shuffle --seed 42", "summary": "Document intelligence on images OR multi-page PDFs with Datalab's Surya OCR 2 (datalab-to/surya-ocr-2, 650M, Qwen3.5-style).", "declared": true }, { "kind": "run", "task": "OCR", "script": "ocr/unlimited-ocr-vllm.py", "repo": "uv-scripts/ocr", "page": "https://huggingface.co/datasets/uv-scripts/ocr/blob/main/unlimited-ocr-vllm.py", "url": "https://huggingface.co/datasets/uv-scripts/ocr/raw/main/unlimited-ocr-vllm.py", "models": [ "baidu/Unlimited-OCR" ], "support": "core", "source": "header", "flavor": "a10g-small", "timeout": null, "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/ocr/raw/main/unlimited-ocr-vllm.py \\\n your-input-dataset your-output-dataset --max-samples 10", "summary": "Convert document images to markdown using Baidu Unlimited-OCR with vLLM.", "declared": true }, { "kind": "run", "task": "OCR", "script": "ocr/unlimited-ocr2-live.py", "repo": "uv-scripts/ocr", "page": "https://huggingface.co/datasets/uv-scripts/ocr/blob/main/unlimited-ocr2-live.py", "url": "https://huggingface.co/datasets/uv-scripts/ocr/raw/main/unlimited-ocr2-live.py", "models": [ "baidu/Unlimited-OCR-2" ], "support": "experimental", "source": "header", "flavor": "rtx-pro-6000", "timeout": "4h", "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/ocr/raw/main/unlimited-ocr2-live.py \\\n \"hf://buckets/biglam/britannica/source/pages/1771EncyclopediaBritannicaNLS/*.jp2\" \\\n /britannica-1771 --live-port 7860", "summary": "unlimited-ocr2.py with a live view you can watch (and screen-record) while the Job runs.", "declared": false }, { "kind": "run", "task": "OCR", "script": "ocr/unlimited-ocr2-saturate.py", "repo": "uv-scripts/ocr", "page": "https://huggingface.co/datasets/uv-scripts/ocr/blob/main/unlimited-ocr2-saturate.py", "url": "https://huggingface.co/datasets/uv-scripts/ocr/raw/main/unlimited-ocr2-saturate.py", "models": [ "baidu/Unlimited-OCR-2" ], "support": "experimental", "source": "header", "flavor": "rtx-pro-6000", "timeout": "4h", "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/ocr/raw/main/unlimited-ocr2-saturate.py \\\n \"hf://buckets/biglam/britannica/source/pages/1771EncyclopediaBritannicaNLS/*.jp2\" \\\n /britannica-1771-uocr2", "summary": "OCR whole documents (book volumes, PDFs) with Baidu Unlimited-OCR-2 via saturate.", "declared": false }, { "kind": "run", "task": "OCR", "script": "ocr/unlimited-ocr2.py", "repo": "uv-scripts/ocr", "page": "https://huggingface.co/datasets/uv-scripts/ocr/blob/main/unlimited-ocr2.py", "url": "https://huggingface.co/datasets/uv-scripts/ocr/raw/main/unlimited-ocr2.py", "models": [ "baidu/Unlimited-OCR-2" ], "support": "core", "source": "header", "flavor": "rtx-pro-6000", "timeout": "4h", "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/ocr/raw/main/unlimited-ocr2.py \\\n \"hf://buckets/biglam/britannica/source/pages/1771EncyclopediaBritannicaNLS/*.jp2\" \\\n /britannica-1771", "summary": "OCR whole documents (book volumes, folders of scans) with Baidu Unlimited-OCR-2.", "declared": true }, { "kind": "run", "task": "Segmentation", "script": "sam3/detect-objects.py", "repo": "uv-scripts/sam3", "page": "https://huggingface.co/datasets/uv-scripts/sam3/blob/main/detect-objects.py", "url": "https://huggingface.co/datasets/uv-scripts/sam3/raw/main/detect-objects.py", "models": [ "facebook/sam3" ], "support": null, "source": "documented", "flavor": null, "timeout": null, "command": "hf jobs uv run --flavor a100-large \\\n -s HF_TOKEN \\\n https://huggingface.co/datasets/uv-scripts/sam3/raw/main/detect-objects.py \\\n INPUT_DATASET OUTPUT_DATASET \\\n --class-name photograph \\\n --confidence-threshold 0.5", "summary": "Detect objects in images using Meta's SAM3 (Segment Anything Model 3).", "declared": true }, { "kind": "run", "task": "Segmentation", "script": "sam3/segment-objects.py", "repo": "uv-scripts/sam3", "page": "https://huggingface.co/datasets/uv-scripts/sam3/blob/main/segment-objects.py", "url": "https://huggingface.co/datasets/uv-scripts/sam3/raw/main/segment-objects.py", "models": [ "facebook/sam3" ], "support": null, "source": "documented", "flavor": null, "timeout": null, "command": "hf jobs uv run --flavor a100-large \\\n -s HF_TOKEN \\\n https://huggingface.co/datasets/uv-scripts/sam3/raw/main/segment-objects.py \\\n INPUT_DATASET OUTPUT_DATASET \\\n --class-name photograph", "summary": "Segment objects in images using Meta's SAM3 (Segment Anything Model 3).", "declared": true }, { "kind": "run", "task": "Transcription", "script": "transcription/cohere-transcribe-vllm.py", "repo": "uv-scripts/transcription", "page": "https://huggingface.co/datasets/uv-scripts/transcription/blob/main/cohere-transcribe-vllm.py", "url": "https://huggingface.co/datasets/uv-scripts/transcription/raw/main/cohere-transcribe-vllm.py", "models": [ "CohereLabs/cohere-transcribe-03-2026" ], "support": null, "source": "flags-needed", "flavor": null, "timeout": null, "command": null, "summary": "Transcribe audio files from a directory using Cohere Transcribe via vLLM.", "declared": false }, { "kind": "run", "task": "Transcription", "script": "transcription/cohere-transcribe.py", "repo": "uv-scripts/transcription", "page": "https://huggingface.co/datasets/uv-scripts/transcription/blob/main/cohere-transcribe.py", "url": "https://huggingface.co/datasets/uv-scripts/transcription/raw/main/cohere-transcribe.py", "models": [ "CohereLabs/cohere-transcribe-03-2026" ], "support": null, "source": "documented", "flavor": null, "timeout": null, "command": "hf jobs uv run --flavor l4x1 \\\n -s HF_TOKEN \\\n -v hf://buckets/your-username/audio-input:/input:ro \\\n -v hf://buckets/your-username/transcripts:/output \\\n https://huggingface.co/datasets/uv-scripts/transcription/raw/main/cohere-transcribe.py \\\n /input /output --language en --compile", "summary": "Transcribe audio files from a directory using Cohere Transcribe via transformers.", "declared": false }, { "kind": "run", "task": "Transcription", "script": "transcription/easytranscriber-transcribe.py", "repo": "uv-scripts/transcription", "page": "https://huggingface.co/datasets/uv-scripts/transcription/blob/main/easytranscriber-transcribe.py", "url": "https://huggingface.co/datasets/uv-scripts/transcription/raw/main/easytranscriber-transcribe.py", "models": [ "CohereLabs/cohere-transcribe-03-2026", "distil-whisper/distil-large-v3.5", "facebook/mms-1b-all" ], "support": null, "source": "documented", "flavor": null, "timeout": null, "command": "hf jobs uv run --flavor l4x1 -s HF_TOKEN \\\n -e UV_TORCH_BACKEND=cu128 \\\n -v hf://buckets/your-username/audio-files:/input:ro \\\n -v hf://buckets/your-username/transcripts-aligned:/output \\\n https://huggingface.co/datasets/uv-scripts/transcription/raw/main/easytranscriber-transcribe.py \\\n /input /output \\\n --language en --emit-txt --emit-srt", "summary": "Transcribe audio with word-level timestamps using kb-labb/easytranscriber.", "declared": false }, { "kind": "run", "task": "Transcription", "script": "transcription/granite-turboctc-transcribe.py", "repo": "uv-scripts/transcription", "page": "https://huggingface.co/datasets/uv-scripts/transcription/blob/main/granite-turboctc-transcribe.py", "url": "https://huggingface.co/datasets/uv-scripts/transcription/raw/main/granite-turboctc-transcribe.py", "models": [ "ibm-granite/granite-speech-5.0-470m-turboctc" ], "support": null, "source": "documented", "flavor": null, "timeout": null, "command": "hf jobs uv run --flavor l4x1 -s HF_TOKEN \\\n -e UV_TORCH_BACKEND=cu128 \\\n -v hf://buckets/your-username/audio-input:/input:ro \\\n -v hf://buckets/your-username/transcripts:/output \\\n https://huggingface.co/datasets/uv-scripts/transcription/raw/main/granite-turboctc-transcribe.py \\\n /input /output", "summary": "Transcribe English audio files with IBM Granite Speech 5.0 TurboCTC (470M).", "declared": false }, { "kind": "run", "task": "Transcription", "script": "transcription/moss-transcribe-diarize-server.py", "repo": "uv-scripts/transcription", "page": "https://huggingface.co/datasets/uv-scripts/transcription/blob/main/moss-transcribe-diarize-server.py", "url": "https://huggingface.co/datasets/uv-scripts/transcription/raw/main/moss-transcribe-diarize-server.py", "models": [ "OpenMOSS-Team/MOSS-Transcribe-Diarize" ], "support": null, "source": "flags-needed", "flavor": null, "timeout": null, "command": null, "summary": "High-throughput transcription + diarization via an in-job sgl-omni server.", "declared": false }, { "kind": "run", "task": "Transcription", "script": "transcription/moss-transcribe-diarize.py", "repo": "uv-scripts/transcription", "page": "https://huggingface.co/datasets/uv-scripts/transcription/blob/main/moss-transcribe-diarize.py", "url": "https://huggingface.co/datasets/uv-scripts/transcription/raw/main/moss-transcribe-diarize.py", "models": [ "OpenMOSS-Team/MOSS-Transcribe-Diarize" ], "support": null, "source": "documented", "flavor": null, "timeout": null, "command": "hf jobs uv run --flavor l4x1 -s HF_TOKEN \\\n -e UV_TORCH_BACKEND=cu128 \\\n -v hf://buckets/your-username/audio-files:/input:ro \\\n -v hf://buckets/your-username/transcripts:/output \\\n https://huggingface.co/datasets/uv-scripts/transcription/raw/main/moss-transcribe-diarize.py \\\n /input /output --emit-txt --emit-srt", "summary": "Transcribe + diarize audio files using MOSS-Transcribe-Diarize (0.9B).", "declared": false }, { "kind": "run", "task": "Transcription", "script": "transcription/nemotron-transcribe.py", "repo": "uv-scripts/transcription", "page": "https://huggingface.co/datasets/uv-scripts/transcription/blob/main/nemotron-transcribe.py", "url": "https://huggingface.co/datasets/uv-scripts/transcription/raw/main/nemotron-transcribe.py", "models": [ "nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B" ], "support": null, "source": "header", "flavor": "rtx-pro-6000", "timeout": "4h", "command": "hf jobs uv run \\\n -v hf://buckets/your-username/audio-files:/input:ro \\\n -v hf://buckets/your-username/transcripts:/output \\\n https://huggingface.co/datasets/uv-scripts/transcription/raw/main/nemotron-transcribe.py \\\n /input /output", "summary": "Transcribe audio with NVIDIA Nemotron 3.5 Transcribe via an in-job vLLM server.", "declared": true }, { "kind": "run", "task": "Video", "script": "video/marlin-caption.py", "repo": "uv-scripts/video", "page": "https://huggingface.co/datasets/uv-scripts/video/blob/main/marlin-caption.py", "url": "https://huggingface.co/datasets/uv-scripts/video/raw/main/marlin-caption.py", "models": [ "NemoStation/Marlin-2B" ], "support": null, "source": "header", "flavor": "a10g-small", "timeout": "2h", "command": "hf jobs uv run \\\n -v hf://buckets/your-username/my-videos:/input:ro \\\n https://huggingface.co/datasets/uv-scripts/video/raw/main/marlin-caption.py \\\n /input hf://buckets/your-username/my-videos/captions", "summary": "Caption videos with timestamped events using Marlin-2B, writing a resumable dataset.", "declared": true }, { "kind": "run", "task": "Video", "script": "video/qwen38-caption.py", "repo": "uv-scripts/video", "page": "https://huggingface.co/datasets/uv-scripts/video/blob/main/qwen38-caption.py", "url": "https://huggingface.co/datasets/uv-scripts/video/raw/main/qwen38-caption.py", "models": [ "Qwen/Qwen3.8-27B" ], "support": null, "source": "header", "flavor": "a100-large", "timeout": "2h", "command": "hf jobs uv run \\\n -v hf://buckets/your-username/my-videos:/input:ro \\\n https://huggingface.co/datasets/uv-scripts/video/raw/main/qwen38-caption.py \\\n /input hf://buckets/your-username/my-videos/captions", "summary": "Caption whole videos — no chunking — with Qwen3.8-27B, writing a resumable dataset.", "declared": true }, { "kind": "run", "task": "Bulk inference", "script": "vllm/generate-responses.py", "repo": "uv-scripts/vllm", "page": "https://huggingface.co/datasets/uv-scripts/vllm/blob/main/generate-responses.py", "url": "https://huggingface.co/datasets/uv-scripts/vllm/raw/main/generate-responses.py", "models": [ "Qwen/Qwen3-30B-A3B-Instruct-2507" ], "support": null, "source": "header", "flavor": "a100-large", "timeout": "2h", "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/vllm/raw/main/generate-responses.py \\\n input output --max-model-len 32768", "summary": "Generate responses for prompts in a dataset using vLLM for efficient GPU inference.", "declared": false }, { "kind": "run", "task": "Bulk inference", "script": "vllm/vlm-classify.py", "repo": "uv-scripts/vllm", "page": "https://huggingface.co/datasets/uv-scripts/vllm/blob/main/vlm-classify.py", "url": "https://huggingface.co/datasets/uv-scripts/vllm/raw/main/vlm-classify.py", "models": [ "Qwen/Qwen2-VL-7B-Instruct" ], "support": null, "source": "header", "flavor": "l40sx1", "timeout": "1h", "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/vllm/raw/main/vlm-classify.py \\\n your-username/INPUT_DATASET \\\n your-username/OUTPUT_DATASET \\\n --classes \"title-page,content,index,other\"", "summary": "Classify images using Vision Language Models with vLLM.", "declared": true }, { "kind": "run", "task": "Object detection", "script": "vlm-object-detection/qwen3vl-detect-fewshot.py", "repo": "uv-scripts/vlm-object-detection", "page": "https://huggingface.co/datasets/uv-scripts/vlm-object-detection/blob/main/qwen3vl-detect-fewshot.py", "url": "https://huggingface.co/datasets/uv-scripts/vlm-object-detection/raw/main/qwen3vl-detect-fewshot.py", "models": [ "Qwen/Qwen3.6-35B-A3B" ], "support": null, "source": "header", "flavor": "a100-large", "timeout": "1h", "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/vlm-object-detection/raw/main/qwen3vl-detect-fewshot.py \\\n INPUT_DATASET OUTPUT_DATASET", "summary": "Instruction-oriented object detection with Qwen3-VL via vLLM.", "declared": true }, { "kind": "run", "task": "Object detection", "script": "vlm-object-detection/qwen3vl-detect.py", "repo": "uv-scripts/vlm-object-detection", "page": "https://huggingface.co/datasets/uv-scripts/vlm-object-detection/blob/main/qwen3vl-detect.py", "url": "https://huggingface.co/datasets/uv-scripts/vlm-object-detection/raw/main/qwen3vl-detect.py", "models": [ "Qwen/Qwen3.6-35B-A3B" ], "support": null, "source": "header", "flavor": "a100-large", "timeout": "1h", "command": "hf jobs uv run \\\n https://huggingface.co/datasets/uv-scripts/vlm-object-detection/raw/main/qwen3vl-detect.py \\\n INPUT_DATASET OUTPUT_DATASET", "summary": "Instruction-oriented object detection with Qwen3-VL via vLLM.", "declared": true } ], "data_tools": [ { "repo": "uv-scripts/object-detection", "description": "Check and convert detection datasets" }, { "repo": "uv-scripts/deduplication", "description": "Remove near-duplicate text" }, { "repo": "uv-scripts/build-atlas", "description": "Build an embedding atlas" }, { "repo": "uv-scripts/iiif-tiles", "description": "Make IIIF deep-zoom tiles" }, { "repo": "uv-scripts/data-processing", "description": "Convert uploads to optimized Parquet" } ] }