From 09942f1c384b5bfd25024f73f2cf2d5e8a25b09d Mon Sep 17 00:00:00 2001 From: Daniel van Strien Date: Fri, 30 Oct 2026 14:20:12 +0000 Subject: [PATCH 1/2] run-on-jobs: open links in a new tab huggingface.co refuses to load inside the Space iframe. Co-Authored-By: Claude Opus 5.5 Claude-Session: https://claude.ai/code/session_016isSPpM5PRqNUzwsDntoG4 --- run-on-jobs/index.html | 3 ++- tools/run-on-jobs-template.html | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/run-on-jobs/index.html b/run-on-jobs/index.html index 9783235..014d2d2 100644 --- a/run-on-jobs/index.html +++ b/run-on-jobs/index.html @@ -2,6 +2,7 @@ + Run on Jobs @@ -86,7 +87,7 @@

Use Hub models on your own data

Run a model over your whole dataset, or fine-tune it on your own examples. Each command starts a job on Hugging Face Jobs and saves the results to the Hub. There is nothing to clone.

Each recipe is a uv script: one Python file that lists its own dependencies, so it runs straight from its URL.

-

Find your model · New to Jobs? Try an example below, or read the quickstart.

+

Find your model · New to Jobs? Try an example below, or read the quickstart.

Read seven scanned NASA pages with GLM-OCR and save the text to a new public dataset on your account. Add --private to keep it private.

hf jobs uv run \
diff --git a/tools/run-on-jobs-template.html b/tools/run-on-jobs-template.html
index 98812b6..8c1976e 100644
--- a/tools/run-on-jobs-template.html
+++ b/tools/run-on-jobs-template.html
@@ -2,6 +2,7 @@
 
 
 
+
 
 Run on Jobs
 
@@ -86,7 +87,7 @@
 
Use Hub models on your own data

 
Run a model over your whole dataset, or fine-tune it on your own examples. Each command starts a job on Hugging Face Jobs and saves the results to the Hub. There is nothing to clone.

 
Each recipe is a uv script: one Python file that lists its own dependencies, so it runs straight from its URL.

-
Find your model · New to Jobs? Try an example below, or read the quickstart.

+
Find your model · New to Jobs? Try an example below, or read the quickstart.

 

 

 
Read seven scanned NASA pages with GLM-OCR and save the text to a new public dataset on your account. Add --private to keep it private.
hf jobs uv run \

From 75fe9fae5e6970671f4147bb46eb9855e119b524 Mon Sep 17 00:00:00 2001
From: Daniel van Strien 
Date: Fri, 30 Oct 2026 14:21:34 +0000
Subject: [PATCH 2/2] run-on-jobs: link models, Hub docs, follow and --help
 pointers

Co-Authored-By: Claude Opus 5.5 
Claude-Session: https://claude.ai/code/session_016isSPpM5PRqNUzwsDntoG4
---
 run-on-jobs/index.html          | 83 +++++++++++++++++----------------
 tools/build-catalog.py          |  1 +
 tools/run-on-jobs-template.html |  7 +--
 3 files changed, 47 insertions(+), 44 deletions(-)

diff --git a/run-on-jobs/index.html b/run-on-jobs/index.html
index 014d2d2..c0067f1 100644
--- a/run-on-jobs/index.html
+++ b/run-on-jobs/index.html
@@ -80,14 +80,15 @@
 
 @media (prefers-reduced-motion:reduce){summary::before{transition:none}}
 .entry{font-size:15px;margin-top:12px}
+.model-link{margin:2px 12px 8px 28px}
 
 
 
 

 
Use Hub models on your own data

 
Run a model over your whole dataset, or fine-tune it on your own examples. Each command starts a job on Hugging Face Jobs and saves the results to the Hub. There is nothing to clone.

-
Each recipe is a uv script: one Python file that lists its own dependencies, so it runs straight from its URL.

-
Find your model · New to Jobs? Try an example below, or read the quickstart.

+
Each recipe is a uv script: one Python file that lists its own dependencies, so it runs straight from its URL.

+
Find your model · New to Jobs? Try an example below, or read the quickstart · Follow uv-scripts for new recipes

 

 

 
Read seven scanned NASA pages with GLM-OCR and save the text to a new public dataset on your account. Add --private to keep it private.
hf jobs uv run \
@@ -233,23 +234,23 @@ 
Use Hub models on your own data

     --num-samples 4 --max-train-pool 2000 --max-eval-samples 100 \
     --max-seq-length 128 --sampling-strategy undersampling --max-minutes 5
Our run: 0.77 accuracy on 100 test articles, against 0.32 for always guessing the most common topic. Training took 20 seconds on cpu-basic.
More recipes and options in uv-scripts/classification.

 

-
You need the hf CLI (1.32 or newer), a login and pay-as-you-go credit. Add --dry-run to see the GPU and settings without starting a job.

+
You need the hf CLI (1.32 or newer), a login and pay-as-you-go credit. Add --dry-run to see the GPU and settings without starting a job, and run hf jobs uv run --help for all options.

 
Find your model

 
Replace the capitalised placeholders and your-username. Check the script if you're unsure what a value should be.

 
 
 
-
OCR
  • allenai/olmOCR-2-7B-1025-FP8command ready · a10g-small
    olmocr2-vllm.py command ready · a10g-small
    Convert document images to markdown using olmOCR-2 with vLLM.
    hf jobs uv run \
+
    OCR
    • allenai/olmOCR-2-7B-1025-FP8command ready · a10g-small
      Open the model page
      olmocr2-vllm.py command ready · a10g-small
      Convert document images to markdown using olmOCR-2 with vLLM.
      hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/ocr/raw/main/olmocr2-vllm.py \
-    INPUT_DATASET OUTPUT_DATASET
      From uv-scripts/ocr, with more options and examples.
    • ATH-MaaS/OvisOCR2command ready · a10g-small
      ovis-ocr2.py command ready · a10g-small
      Convert document images to markdown using OvisOCR2 with vLLM.
      hf jobs uv run \
+    INPUT_DATASET OUTPUT_DATASET
      From uv-scripts/ocr, with more options and examples.
    • ATH-MaaS/OvisOCR2command ready · a10g-small
      Open the model page
      ovis-ocr2.py command ready · a10g-small
      Convert document images to markdown using OvisOCR2 with vLLM.
      hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/ocr/raw/main/ovis-ocr2.py \
     INPUT_DATASET OUTPUT_DATASET --batch-size 16
      From uv-scripts/ocr, with more options and examples.
      1 more recipe
      ovis-ocr2-saturate.py command ready · a10g-small
      Convert document images to markdown using OvisOCR2 via saturate.
      hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/ocr/raw/main/ovis-ocr2-saturate.py \
-    <INPUT_DATASET> <OUTPUT_DATASET>
      From uv-scripts/ocr, with more options and examples.
    • baidu/Qianfan-OCRcommand ready · a10g-small
      qianfan-ocr.py command ready · a10g-small
      Convert document images to markdown using Qianfan-OCR with vLLM.
      hf jobs uv run \
+    <INPUT_DATASET> <OUTPUT_DATASET>
      From uv-scripts/ocr, with more options and examples.
  • baidu/Qianfan-OCRcommand ready · a10g-small
    Open the model page
    qianfan-ocr.py command ready · a10g-small
    Convert document images to markdown using Qianfan-OCR with vLLM.
    hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/ocr/raw/main/qianfan-ocr.py \
-    INPUT_DATASET OUTPUT_DATASET --max-samples 10
    From uv-scripts/ocr, with more options and examples.
  • baidu/Unlimited-OCRcommand ready · a10g-small
    unlimited-ocr-vllm.py command ready · a10g-small
    Convert document images to markdown using Baidu Unlimited-OCR with vLLM.
    hf jobs uv run \
+    INPUT_DATASET OUTPUT_DATASET --max-samples 10
    From uv-scripts/ocr, with more options and examples.
  • baidu/Unlimited-OCRcommand ready · a10g-small
    Open the model page
    unlimited-ocr-vllm.py command ready · a10g-small
    Convert document images to markdown using Baidu Unlimited-OCR with vLLM.
    hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/ocr/raw/main/unlimited-ocr-vllm.py \
-    your-input-dataset your-output-dataset --max-samples 10
    From uv-scripts/ocr, with more options and examples.
  • baidu/Unlimited-OCR-2command ready · rtx-pro-6000
    unlimited-ocr2.py command ready · rtx-pro-6000
    OCR whole documents (book volumes, folders of scans) with Baidu Unlimited-OCR-2.
    hf jobs uv run \
+    your-input-dataset your-output-dataset --max-samples 10
    From uv-scripts/ocr, with more options and examples.
  • baidu/Unlimited-OCR-2command ready · rtx-pro-6000
    Open the model page
    unlimited-ocr2.py command ready · rtx-pro-6000
    OCR whole documents (book volumes, folders of scans) with Baidu Unlimited-OCR-2.
    hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/ocr/raw/main/unlimited-ocr2.py \
     "hf://buckets/biglam/britannica/source/pages/1771EncyclopediaBritannicaNLS/*.jp2" \
     <user>/britannica-1771
    From uv-scripts/ocr, with more options and examples.
    2 more recipes
    unlimited-ocr2-live.py command ready, experimental · rtx-pro-6000
    unlimited-ocr2.py with a live view you can watch (and screen-record) while the Job runs.
    hf jobs uv run \
@@ -258,45 +259,45 @@ 
    Find your model
    
     <user>/britannica-1771 --live-port 7860
    From uv-scripts/ocr, with more options and examples.
    unlimited-ocr2-saturate.py command ready, experimental · rtx-pro-6000
    OCR whole documents (book volumes, PDFs) with Baidu Unlimited-OCR-2 via saturate.
    hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/ocr/raw/main/unlimited-ocr2-saturate.py \
     "hf://buckets/biglam/britannica/source/pages/1771EncyclopediaBritannicaNLS/*.jp2" \
-    <user>/britannica-1771-uocr2
    From uv-scripts/ocr, with more options and examples.
  • datalab-to/liftcommand ready · a100-large
    lift-extract.py command ready · a100-large
    Extract structured JSON from document images OR multi-page PDFs using Datalab's lift model (datalab-to/lift, 9B, Qwen3.5-based).
    hf jobs uv run \
+    <user>/britannica-1771-uocr2
    From uv-scripts/ocr, with more options and examples.
  • datalab-to/liftcommand ready · a100-large
    Open the model page
    lift-extract.py command ready · a100-large
    Extract structured JSON from document images OR multi-page PDFs using Datalab's lift model (datalab-to/lift, 9B, Qwen3.5-based).
    hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/ocr/raw/main/lift-extract.py \
     INPUT_DATASET OUTPUT_DATASET \
     --schema '{"type":"object","properties":{"title":{"type":"string"}}}' \
-    --max-samples 5 --shuffle --seed 42
    From uv-scripts/ocr, with more options and examples.
  • datalab-to/surya-ocr-2command ready · a10g-small
    surya-ocr.py command ready · a10g-small
    Document intelligence on images OR multi-page PDFs with Datalab's Surya OCR 2 (datalab-to/surya-ocr-2, 650M, Qwen3.5-style).
    hf jobs uv run \
+    --max-samples 5 --shuffle --seed 42
    From uv-scripts/ocr, with more options and examples.
  • datalab-to/surya-ocr-2command ready · a10g-small
    Open the model page
    surya-ocr.py command ready · a10g-small
    Document intelligence on images OR multi-page PDFs with Datalab's Surya OCR 2 (datalab-to/surya-ocr-2, 650M, Qwen3.5-style).
    hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/ocr/raw/main/surya-ocr.py \
     INPUT_DATASET OUTPUT_DATASET \
-    --max-samples 5 --shuffle --seed 42
    From uv-scripts/ocr, with more options and examples.
  • deepseek-ai/DeepSeek-OCRcommand ready · a10g-small
    deepseek-ocr-vllm.py command ready · a10g-small
    Convert document images to markdown using DeepSeek-OCR with vLLM.
    hf jobs uv run \
+    --max-samples 5 --shuffle --seed 42
    From uv-scripts/ocr, with more options and examples.
  • deepseek-ai/DeepSeek-OCRcommand ready · a10g-small
    Open the model page
    deepseek-ocr-vllm.py command ready · a10g-small
    Convert document images to markdown using DeepSeek-OCR with vLLM.
    hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/ocr/raw/main/deepseek-ocr-vllm.py \
-    my-dataset my-output --max-samples 10
    From uv-scripts/ocr, with more options and examples.
  • deepseek-ai/DeepSeek-OCR-2command ready · a10g-small
    deepseek-ocr2-vllm.py command ready · a10g-small
    Convert document images to markdown using DeepSeek-OCR-2 with vLLM.
    hf jobs uv run \
+    my-dataset my-output --max-samples 10
    From uv-scripts/ocr, with more options and examples.
  • deepseek-ai/DeepSeek-OCR-2command ready · a10g-small
    Open the model page
    deepseek-ocr2-vllm.py command ready · a10g-small
    Convert document images to markdown using DeepSeek-OCR-2 with vLLM.
    hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/ocr/raw/main/deepseek-ocr2-vllm.py \
-    my-dataset my-output --max-samples 10
    From uv-scripts/ocr, with more options and examples.
  • lightonai/LightOnOCR-2-1Bcommand ready · a10g-small
    lighton-ocr2.py command ready · a10g-small
    Convert document images to markdown using LightOnOCR-2 with vLLM.
    hf jobs uv run \
+    my-dataset my-output --max-samples 10
    From uv-scripts/ocr, with more options and examples.
  • lightonai/LightOnOCR-2-1Bcommand ready · a10g-small
    Open the model page
    lighton-ocr2.py command ready · a10g-small
    Convert document images to markdown using LightOnOCR-2 with vLLM.
    hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/ocr/raw/main/lighton-ocr2.py \
     <INPUT_DATASET> <OUTPUT_DATASET>
    From uv-scripts/ocr, with more options and examples.
    1 more recipe
    lighton-ocr2-saturate.py command ready · a10g-small
    Convert document images to markdown using LightOnOCR-2 via saturate.
    hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/ocr/raw/main/lighton-ocr2-saturate.py \
-    <INPUT_DATASET> <OUTPUT_DATASET>
    From uv-scripts/ocr, with more options and examples.
  • lightonai/LightOnOCR-3-4Bcommand ready · a10g-small
    lighton-ocr3-bucket.py command ready · a10g-small
    OCR images and PDFs from an HF Bucket (or a directory) using LightOnOCR-3, writing markdown files.
    hf jobs uv run \
+    <INPUT_DATASET> <OUTPUT_DATASET>
    From uv-scripts/ocr, with more options and examples.
  • lightonai/LightOnOCR-3-4Bcommand ready · a10g-small
    Open the model page
    lighton-ocr3-bucket.py command ready · a10g-small
    OCR images and PDFs from an HF Bucket (or a directory) using LightOnOCR-3, writing markdown files.
    hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/ocr/raw/main/lighton-ocr3-bucket.py \
     hf://buckets/biglam/britannica/source/pages/00070476bsb \
     hf://buckets/your-username/ocr-output/britannica --mode grounding --max-samples 20
    From uv-scripts/ocr, with more options and examples.
    1 more recipe
    lighton-ocr3.py command ready · a10g-small
    Convert document images to markdown (or layout blocks) using LightOnOCR-3 with vLLM.
    hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/ocr/raw/main/lighton-ocr3.py \
-    INPUT_DATASET OUTPUT_DATASET --max-samples 10
    From uv-scripts/ocr, with more options and examples.
  • numind/NuExtract3command ready · a10g-small
    nuextract3.py command ready · a10g-small
    Convert document images to markdown OR extract structured JSON using NuExtract3 with vLLM.
    hf jobs uv run \
+    INPUT_DATASET OUTPUT_DATASET --max-samples 10
    From uv-scripts/ocr, with more options and examples.
  • numind/NuExtract3command ready · a10g-small
    Open the model page
    nuextract3.py command ready · a10g-small
    Convert document images to markdown OR extract structured JSON using NuExtract3 with vLLM.
    hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/ocr/raw/main/nuextract3.py \
-    INPUT_DATASET OUTPUT_DATASET --max-samples 5 --shuffle --seed 42
    From uv-scripts/ocr, with more options and examples.
  • openbmb/MiniCPM-OCR-1.0command ready · a10g-large
    minicpm-ocr.py command ready, experimental · a10g-large
    Convert document images to markdown with OpenBMB's MiniCPM-OCR 1.0 pipeline.
    hf jobs uv run \
+    INPUT_DATASET OUTPUT_DATASET --max-samples 5 --shuffle --seed 42
    From uv-scripts/ocr, with more options and examples.
  • openbmb/MiniCPM-OCR-1.0command ready · a10g-large
    Open the model page
    minicpm-ocr.py command ready, experimental · a10g-large
    Convert document images to markdown with OpenBMB's MiniCPM-OCR 1.0 pipeline.
    hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/ocr/raw/main/minicpm-ocr.py \
-    INPUT_DATASET OUTPUT_DATASET --max-samples 20
    From uv-scripts/ocr, with more options and examples.
  • PaddlePaddle/PaddleOCR-VL-1.6command ready · a10g-small
    paddleocr-vl-1.6.py command ready · a10g-small
    Convert document images to text/tables/formulas using PaddleOCR-VL-1.6 with vLLM.
    hf jobs uv run \
+    INPUT_DATASET OUTPUT_DATASET --max-samples 20
    From uv-scripts/ocr, with more options and examples.
  • PaddlePaddle/PaddleOCR-VL-1.6command ready · a10g-small
    Open the model page
    paddleocr-vl-1.6.py command ready · a10g-small
    Convert document images to text/tables/formulas using PaddleOCR-VL-1.6 with vLLM.
    hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/ocr/raw/main/paddleocr-vl-1.6.py \
-    INPUT_DATASET OUTPUT_DATASET
    From uv-scripts/ocr, with more options and examples.
  • rednote-hilab/dots.mocrcommand ready · a10g-small
    dots-mocr.py command ready · a10g-small
    Convert document images to markdown using dots.mocr with vLLM.
    hf jobs uv run \
+    INPUT_DATASET OUTPUT_DATASET
    From uv-scripts/ocr, with more options and examples.
  • rednote-hilab/dots.mocrcommand ready · a10g-small
    Open the model page
    dots-mocr.py command ready · a10g-small
    Convert document images to markdown using dots.mocr with vLLM.
    hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/ocr/raw/main/dots-mocr.py \
-    INPUT_DATASET OUTPUT_DATASET
    From uv-scripts/ocr, with more options and examples.
  • rednote-hilab/dots.ocrcommand ready · a10g-small
    dots-ocr.py command ready · a10g-small
    Convert document images to markdown using DoTS.ocr with vLLM.
    hf jobs uv run \
+    INPUT_DATASET OUTPUT_DATASET
    From uv-scripts/ocr, with more options and examples.
  • rednote-hilab/dots.ocrcommand ready · a10g-small
    Open the model page
    dots-ocr.py command ready · a10g-small
    Convert document images to markdown using DoTS.ocr with vLLM.
    hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/ocr/raw/main/dots-ocr.py \
-    INPUT_DATASET OUTPUT_DATASET
    From uv-scripts/ocr, with more options and examples.
  • tencent/HunyuanOCRcommand ready · a10g-small
    hunyuan-ocr-1.5.py command ready · a10g-small
    Convert document images to markdown using HunyuanOCR-1.5 with vLLM.
    hf jobs uv run \
+    INPUT_DATASET OUTPUT_DATASET
    From uv-scripts/ocr, with more options and examples.
  • tencent/HunyuanOCRcommand ready · a10g-small
    Open the model page
    hunyuan-ocr-1.5.py command ready · a10g-small
    Convert document images to markdown using HunyuanOCR-1.5 with vLLM.
    hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/ocr/raw/main/hunyuan-ocr-1.5.py \
-    INPUT_DATASET OUTPUT_DATASET
    From uv-scripts/ocr, with more options and examples.
  • zai-org/GLM-OCRcommand ready · a10g-small
    glm-ocr.py command ready · a10g-small
    Convert document images to markdown using GLM-OCR with vLLM.
    hf jobs uv run \
+    INPUT_DATASET OUTPUT_DATASET
    From uv-scripts/ocr, with more options and examples.
  • zai-org/GLM-OCRcommand ready · a10g-small
    Open the model page
    glm-ocr.py command ready · a10g-small
    Convert document images to markdown using GLM-OCR with vLLM.
    hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/ocr/raw/main/glm-ocr.py \
     {source_dataset} \
     <OUTPUT_DATASET> \
     --image-column {image_column} \
     --batch-size {batch_size} \
-    --task {task}
    From uv-scripts/ocr, with more options and examples.
Transcription
  • CohereLabs/cohere-transcribe-03-2026example command
    cohere-transcribe.py example command
    Transcribe audio files from a directory using Cohere Transcribe via transformers.
    hf jobs uv run --flavor l4x1 \
+    --task {task}
    From uv-scripts/ocr, with more options and examples.
Transcription
  • CohereLabs/cohere-transcribe-03-2026example command
    Open the model page
    cohere-transcribe.py example command
    Transcribe audio files from a directory using Cohere Transcribe via transformers.
    hf jobs uv run --flavor l4x1 \
     -s HF_TOKEN \
     -v hf://buckets/your-username/audio-input:/input:ro \
     -v hf://buckets/your-username/transcripts:/output \
@@ -307,33 +308,33 @@ 
    Find your model
    
     -v hf://buckets/your-username/transcripts-aligned:/output \
     https://huggingface.co/datasets/uv-scripts/transcription/raw/main/easytranscriber-transcribe.py \
     /input /output \
-    --language en --emit-txt --emit-srt
    From uv-scripts/transcription, with more options and examples.
    cohere-transcribe-vllm.py read the script first
    Transcribe audio files from a directory using Cohere Transcribe via vLLM.
    Read the script for its options. There is no ready-made command yet.
    From uv-scripts/transcription, with more options and examples.
  • distil-whisper/distil-large-v3.5example command
    easytranscriber-transcribe.py example command
    Transcribe audio with word-level timestamps using kb-labb/easytranscriber.
    hf jobs uv run --flavor l4x1 -s HF_TOKEN \
+    --language en --emit-txt --emit-srt
    From uv-scripts/transcription, with more options and examples.
    cohere-transcribe-vllm.py read the script first
    Transcribe audio files from a directory using Cohere Transcribe via vLLM.
    Read the script for its options. There is no ready-made command yet.
    From uv-scripts/transcription, with more options and examples.
  • distil-whisper/distil-large-v3.5example command
    Open the model page
    easytranscriber-transcribe.py example command
    Transcribe audio with word-level timestamps using kb-labb/easytranscriber.
    hf jobs uv run --flavor l4x1 -s HF_TOKEN \
     -e UV_TORCH_BACKEND=cu128 \
     -v hf://buckets/your-username/audio-files:/input:ro \
     -v hf://buckets/your-username/transcripts-aligned:/output \
     https://huggingface.co/datasets/uv-scripts/transcription/raw/main/easytranscriber-transcribe.py \
     /input /output \
-    --language en --emit-txt --emit-srt
    From uv-scripts/transcription, with more options and examples.
  • facebook/mms-1b-allexample command
    easytranscriber-transcribe.py example command
    Transcribe audio with word-level timestamps using kb-labb/easytranscriber.
    hf jobs uv run --flavor l4x1 -s HF_TOKEN \
+    --language en --emit-txt --emit-srt
    From uv-scripts/transcription, with more options and examples.
  • facebook/mms-1b-allexample command
    Open the model page
    easytranscriber-transcribe.py example command
    Transcribe audio with word-level timestamps using kb-labb/easytranscriber.
    hf jobs uv run --flavor l4x1 -s HF_TOKEN \
     -e UV_TORCH_BACKEND=cu128 \
     -v hf://buckets/your-username/audio-files:/input:ro \
     -v hf://buckets/your-username/transcripts-aligned:/output \
     https://huggingface.co/datasets/uv-scripts/transcription/raw/main/easytranscriber-transcribe.py \
     /input /output \
-    --language en --emit-txt --emit-srt
    From uv-scripts/transcription, with more options and examples.
  • ibm-granite/granite-speech-5.0-470m-turboctcexample command
    granite-turboctc-transcribe.py example command
    Transcribe English audio files with IBM Granite Speech 5.0 TurboCTC (470M).
    hf jobs uv run --flavor l4x1 -s HF_TOKEN \
+    --language en --emit-txt --emit-srt
    From uv-scripts/transcription, with more options and examples.
  • ibm-granite/granite-speech-5.0-470m-turboctcexample command
    Open the model page
    granite-turboctc-transcribe.py example command
    Transcribe English audio files with IBM Granite Speech 5.0 TurboCTC (470M).
    hf jobs uv run --flavor l4x1 -s HF_TOKEN \
     -e UV_TORCH_BACKEND=cu128 \
     -v hf://buckets/your-username/audio-input:/input:ro \
     -v hf://buckets/your-username/transcripts:/output \
     https://huggingface.co/datasets/uv-scripts/transcription/raw/main/granite-turboctc-transcribe.py \
-    /input /output
    From uv-scripts/transcription, with more options and examples.
  • nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4Bcommand ready · rtx-pro-6000
    nemotron-transcribe.py command ready · rtx-pro-6000
    Transcribe audio with NVIDIA Nemotron 3.5 Transcribe via an in-job vLLM server.
    hf jobs uv run \
+    /input /output
    From uv-scripts/transcription, with more options and examples.
  • nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4Bcommand ready · rtx-pro-6000
    Open the model page
    nemotron-transcribe.py command ready · rtx-pro-6000
    Transcribe audio with NVIDIA Nemotron 3.5 Transcribe via an in-job vLLM server.
    hf jobs uv run \
     -v hf://buckets/your-username/audio-files:/input:ro \
     -v hf://buckets/your-username/transcripts:/output \
     https://huggingface.co/datasets/uv-scripts/transcription/raw/main/nemotron-transcribe.py \
-    /input /output
    From uv-scripts/transcription, with more options and examples.
  • OpenMOSS-Team/MOSS-Transcribe-Diarizeexample command
    moss-transcribe-diarize.py example command
    Transcribe + diarize audio files using MOSS-Transcribe-Diarize (0.9B).
    hf jobs uv run --flavor l4x1 -s HF_TOKEN \
+    /input /output
    From uv-scripts/transcription, with more options and examples.
  • OpenMOSS-Team/MOSS-Transcribe-Diarizeexample command
    Open the model page
    moss-transcribe-diarize.py example command
    Transcribe + diarize audio files using MOSS-Transcribe-Diarize (0.9B).
    hf jobs uv run --flavor l4x1 -s HF_TOKEN \
     -e UV_TORCH_BACKEND=cu128 \
     -v hf://buckets/your-username/audio-files:/input:ro \
     -v hf://buckets/your-username/transcripts:/output \
     https://huggingface.co/datasets/uv-scripts/transcription/raw/main/moss-transcribe-diarize.py \
-    /input /output --emit-txt --emit-srt
    From uv-scripts/transcription, with more options and examples.
    1 more recipe
    moss-transcribe-diarize-server.py read the script first
    High-throughput transcription + diarization via an in-job sgl-omni server.
    Read the script for its options. There is no ready-made command yet.
    From uv-scripts/transcription, with more options and examples.
Segmentation
Segmentation
  • facebook/sam3example command
    Open the model page
    detect-objects.py example command
    Detect objects in images using Meta's SAM3 (Segment Anything Model 3).
    hf jobs uv run --flavor a100-large \
     -s HF_TOKEN \
     https://huggingface.co/datasets/uv-scripts/sam3/raw/main/detect-objects.py \
     INPUT_DATASET OUTPUT_DATASET \
@@ -342,20 +343,20 @@ 
    Find your model
    
     -s HF_TOKEN \
     https://huggingface.co/datasets/uv-scripts/sam3/raw/main/segment-objects.py \
     INPUT_DATASET OUTPUT_DATASET \
-    --class-name photograph
    From uv-scripts/sam3, with more options and examples.
Object detection
  • Qwen/Qwen3.6-35B-A3Bcommand ready · a100-large
    qwen3vl-detect.py command ready · a100-large
    Instruction-oriented object detection with Qwen3-VL via vLLM.
    hf jobs uv run \
+    --class-name photograph
    From uv-scripts/sam3, with more options and examples.
Object detection
  • Qwen/Qwen3.6-35B-A3Bcommand ready · a100-large
    Open the model page
    qwen3vl-detect.py command ready · a100-large
    Instruction-oriented object detection with Qwen3-VL via vLLM.
    hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/vlm-object-detection/raw/main/qwen3vl-detect.py \
     INPUT_DATASET OUTPUT_DATASET
    From uv-scripts/vlm-object-detection, with more options and examples.
    1 more recipe
    qwen3vl-detect-fewshot.py command ready · a100-large
    Instruction-oriented object detection with Qwen3-VL via vLLM.
    hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/vlm-object-detection/raw/main/qwen3vl-detect-fewshot.py \
-    INPUT_DATASET OUTPUT_DATASET
    From uv-scripts/vlm-object-detection, with more options and examples.
Video
  • NemoStation/Marlin-2Bcommand ready · a10g-small
    marlin-caption.py command ready · a10g-small
    Caption videos with timestamped events using Marlin-2B, writing a resumable dataset.
    hf jobs uv run \
+    INPUT_DATASET OUTPUT_DATASET
    From uv-scripts/vlm-object-detection, with more options and examples.
Video
  • NemoStation/Marlin-2Bcommand ready · a10g-small
    Open the model page
    marlin-caption.py command ready · a10g-small
    Caption videos with timestamped events using Marlin-2B, writing a resumable dataset.
    hf jobs uv run \
     -v hf://buckets/your-username/my-videos:/input:ro \
     https://huggingface.co/datasets/uv-scripts/video/raw/main/marlin-caption.py \
-    /input hf://buckets/your-username/my-videos/captions
    From uv-scripts/video, with more options and examples.
  • Qwen/Qwen3.8-27Bcommand ready · a100-large
    qwen38-caption.py command ready · a100-large
    Caption whole videos — no chunking — with Qwen3.8-27B, writing a resumable dataset.
    hf jobs uv run \
+    /input hf://buckets/your-username/my-videos/captions
    From uv-scripts/video, with more options and examples.
  • Qwen/Qwen3.8-27Bcommand ready · a100-large
    Open the model page
    qwen38-caption.py command ready · a100-large
    Caption whole videos — no chunking — with Qwen3.8-27B, writing a resumable dataset.
    hf jobs uv run \
     -v hf://buckets/your-username/my-videos:/input:ro \
     https://huggingface.co/datasets/uv-scripts/video/raw/main/qwen38-caption.py \
-    /input hf://buckets/your-username/my-videos/captions
    From uv-scripts/video, with more options and examples.
Classification
  • fastino/gliner2.5-multi-v1command ready · t4-small
    classify-gliner2.py command ready · t4-small
    Classify a text column of a Hub dataset with GLiNER2 — zero-shot, or with your fine-tuned model.
    hf jobs uv run \
+    /input hf://buckets/your-username/my-videos/captions
    From uv-scripts/video, with more options and examples.
Classification
  • fastino/gliner2.5-multi-v1command ready · t4-small
    Open the model page
    classify-gliner2.py command ready · t4-small
    Classify a text column of a Hub dataset with GLiNER2 — zero-shot, or with your fine-tuned model.
    hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/classification/raw/main/classify-gliner2.py \
     fancyzhx/ag_news your-username/ag-news-gliner2 \
-    --labels World Sports Business "Science and technology" --max-samples 1000
    From uv-scripts/classification, with more options and examples.
  • HuggingFaceTB/SmolLM3-3Bcommand ready · l4x1
    classify-dataset-sglang.py command ready · l4x1
    Classify text columns in Hugging Face datasets using SGLang with reasoning-aware models.
    hf jobs uv run \
+    --labels World Sports Business "Science and technology" --max-samples 1000
    From uv-scripts/classification, with more options and examples.
  • HuggingFaceTB/SmolLM3-3Bcommand ready · l4x1
    Open the model page
    classify-dataset-sglang.py command ready · l4x1
    Classify text columns in Hugging Face datasets using SGLang with reasoning-aware models.
    hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/classification/raw/main/classify-dataset-sglang.py \
     --input-dataset your-username/emails \
     --column content \
@@ -367,26 +368,26 @@ 
    Find your model
    
     --column content \
     --labels "spam,ham" \
     --output-dataset your-username/emails-classified \
-    --enable-reasoning
    From uv-scripts/classification, with more options and examples.
Embeddings
  • BAAI/bge-base-en-v1.5example command
    embed-to-lance.py example command
    Embed a Hugging Face dataset and push it back as a Lance vector index — a Hub dataset that IS a searchable vector database.
    hf jobs uv run --flavor l4x1 -s HF_TOKEN \
+    --enable-reasoning
    From uv-scripts/classification, with more options and examples.
Embeddings
  • BAAI/bge-base-en-v1.5example command
    Open the model page
    embed-to-lance.py example command
    Embed a Hugging Face dataset and push it back as a Lance vector index — a Hub dataset that IS a searchable vector database.
    hf jobs uv run --flavor l4x1 -s HF_TOKEN \
     https://huggingface.co/datasets/uv-scripts/embeddings/raw/main/embed-to-lance.py \
-    stanfordnlp/imdb your-username/imdb-vecdb --column text --model BAAI/bge-base-en-v1.5 --private
    From uv-scripts/embeddings, with more options and examples.
  • Qwen/Qwen3-Embedding-0.6Bexample command
    generate-embeddings-vllm.py example command
    High-throughput embedding generation with vLLM pooling mode — the "scale" variant of generate-embeddings.py, for large decoder embedding models (e.g.
    hf jobs uv run --flavor l4x1 -s HF_TOKEN \
+    stanfordnlp/imdb your-username/imdb-vecdb --column text --model BAAI/bge-base-en-v1.5 --private
    From uv-scripts/embeddings, with more options and examples.
  • Qwen/Qwen3-Embedding-0.6Bexample command
    Open the model page
    generate-embeddings-vllm.py example command
    High-throughput embedding generation with vLLM pooling mode — the "scale" variant of generate-embeddings.py, for large decoder embedding models (e.g.
    hf jobs uv run --flavor l4x1 -s HF_TOKEN \
     https://huggingface.co/datasets/uv-scripts/embeddings/raw/main/generate-embeddings-vllm.py \
-    stanfordnlp/imdb your-username/imdb-embeddings --column text --model Qwen/Qwen3-Embedding-0.6B --private
    From uv-scripts/embeddings, with more options and examples.
  • sentence-transformers/all-MiniLM-L6-v2example command
    generate-embeddings.py example command
    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…
    hf jobs uv run --flavor l4x1 -s HF_TOKEN \
+    stanfordnlp/imdb your-username/imdb-embeddings --column text --model Qwen/Qwen3-Embedding-0.6B --private
    From uv-scripts/embeddings, with more options and examples.
  • sentence-transformers/all-MiniLM-L6-v2example command
    Open the model page
    generate-embeddings.py example command
    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…
    hf jobs uv run --flavor l4x1 -s HF_TOKEN \
     https://huggingface.co/datasets/uv-scripts/embeddings/raw/main/generate-embeddings.py \
     stanfordnlp/imdb  your-username/imdb-embeddings \
-    --column text --model sentence-transformers/all-MiniLM-L6-v2
    From uv-scripts/embeddings, with more options and examples.
    1 more recipe
    launch-embedding-fleet.py read the script first
    Fan one embedding run out across N Hugging Face Jobs, then consolidate.
    Read the script for its options. There is no ready-made command yet.
    From uv-scripts/embeddings, with more options and examples.
Text generation
  • Qwen/Qwen2-VL-7B-Instructcommand ready · l40sx1
    vlm-classify.py command ready · l40sx1
    Classify images using Vision Language Models with vLLM.
    hf jobs uv run \
+    --column text --model sentence-transformers/all-MiniLM-L6-v2
    From uv-scripts/embeddings, with more options and examples.
    1 more recipe
    launch-embedding-fleet.py read the script first
    Fan one embedding run out across N Hugging Face Jobs, then consolidate.
    Read the script for its options. There is no ready-made command yet.
    From uv-scripts/embeddings, with more options and examples.
Text generation
  • Qwen/Qwen2-VL-7B-Instructcommand ready · l40sx1
    Open the model page
    vlm-classify.py command ready · l40sx1
    Classify images using Vision Language Models with vLLM.
    hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/vllm/raw/main/vlm-classify.py \
     your-username/INPUT_DATASET \
     your-username/OUTPUT_DATASET \
-    --classes "title-page,content,index,other"
    From uv-scripts/vllm, with more options and examples.
  • Qwen/Qwen3-30B-A3B-Instruct-2507command ready · a100-large
    generate-responses.py command ready · a100-large
    Generate responses for prompts in a dataset using vLLM for efficient GPU inference.
    hf jobs uv run \
+    --classes "title-page,content,index,other"
    From uv-scripts/vllm, with more options and examples.
  • Qwen/Qwen3-30B-A3B-Instruct-2507command ready · a100-large
    Open the model page
    generate-responses.py command ready · a100-large
    Generate responses for prompts in a dataset using vLLM for efficient GPU inference.
    hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/vllm/raw/main/generate-responses.py \
-    input output --max-model-len 32768
    From uv-scripts/vllm, with more options and examples.
Fine-tuning
  • fastino/gliner2.5-multi-v1command ready · t4-small
    train-gliner2.py command ready · t4-small
    Fine-tune GLiNER2 into a text classifier — a small model (74M to 287M parameters, depending on the base checkpoint) that already works zero-shot.
    hf jobs uv run \
+    input output --max-model-len 32768
    From uv-scripts/vllm, with more options and examples.
Fine-tuning
  • fastino/gliner2.5-multi-v1command ready · t4-small
    Open the model page
    train-gliner2.py command ready · t4-small
    Fine-tune GLiNER2 into a text classifier — a small model (74M to 287M parameters, depending on the base checkpoint) that already works zero-shot.
    hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/classification/raw/main/train-gliner2.py \
     biglam/blbooksgenre your-username/gliner2-blbooks-genre \
-    --dataset-config title_genre_classifiction --text-column title
    From uv-scripts/classification, with more options and examples.
  • LiquidAI/LFM2.5-Encoder-350Mcommand ready · l4x1
    train-classifier.py command ready · l4x1
    Fine-tune a text-classification encoder on a Hub dataset and push the trained model to the Hub.
    hf jobs uv run \
+    --dataset-config title_genre_classifiction --text-column title
    From uv-scripts/classification, with more options and examples.
  • LiquidAI/LFM2.5-Encoder-350Mcommand ready · l4x1
    Open the model page
    train-classifier.py command ready · l4x1
    Fine-tune a text-classification encoder on a Hub dataset and push the trained model to the Hub.
    hf jobs uv run \
     https://huggingface.co/datasets/uv-scripts/classification/raw/main/train-classifier.py \
     fancyzhx/ag_news your-username/my-news-classifier \
-    --max-samples 2000 --epochs 1
    From uv-scripts/classification, with more options and examples.
  • sentence-transformers/all-MiniLM-L6-v2example command
    train-setfit.py example command
    Few-shot text classification with SetFit — train on 8-64 labelled examples per class, on CPU or GPU.
    hf jobs uv run --flavor cpu-basic --secrets HF_TOKEN \
+    --max-samples 2000 --epochs 1
    From uv-scripts/classification, with more options and examples.
  • sentence-transformers/all-MiniLM-L6-v2example command
    Open the model page
    train-setfit.py example command
    Few-shot text classification with SetFit — train on 8-64 labelled examples per class, on CPU or GPU.
    hf jobs uv run --flavor cpu-basic --secrets HF_TOKEN \
     https://huggingface.co/datasets/uv-scripts/classification/raw/main/train-setfit.py \
     fancyzhx/ag_news your-username/ag-news-setfit \
     --num-samples 8
    From uv-scripts/classification, with more options and examples.

diff --git a/tools/build-catalog.py b/tools/build-catalog.py
index 1f01231..7bdf899 100755
--- a/tools/build-catalog.py
+++ b/tools/build-catalog.py
@@ -303,6 +303,7 @@ def model_row_html(task, model, recipes):
     return (
         f'
  • '
         f'{html.escape(model)}{html.escape(row_status)}'
+        + f'
    Open the model page
    '
         + recipe_html(best) + more + "
    • "
     )
 
diff --git a/tools/run-on-jobs-template.html b/tools/run-on-jobs-template.html
index 8c1976e..eb818cf 100644
--- a/tools/run-on-jobs-template.html
+++ b/tools/run-on-jobs-template.html
@@ -80,14 +80,15 @@
 
 @media (prefers-reduced-motion:reduce){summary::before{transition:none}}
 .entry{font-size:15px;margin-top:12px}
+.model-link{margin:2px 12px 8px 28px}
 
 
 
 
    
 
    Use Hub models on your own data
    
 
    Run a model over your whole dataset, or fine-tune it on your own examples. Each command starts a job on Hugging Face Jobs and saves the results to the Hub. There is nothing to clone.
    
-
    Each recipe is a uv script: one Python file that lists its own dependencies, so it runs straight from its URL.
    
-
    Find your model · New to Jobs? Try an example below, or read the quickstart.
    
+
    Each recipe is a uv script: one Python file that lists its own dependencies, so it runs straight from its URL.
    
+
    Find your model · New to Jobs? Try an example below, or read the quickstart · Follow uv-scripts for new recipes
    
 
    
 
    
 
    Read seven scanned NASA pages with GLM-OCR and save the text to a new public dataset on your account. Add --private to keep it private.
    hf jobs uv run \
@@ -233,7 +234,7 @@ 
    Use Hub models on your own data
    
     --num-samples 4 --max-train-pool 2000 --max-eval-samples 100 \
     --max-seq-length 128 --sampling-strategy undersampling --max-minutes 5
    Our run: 0.77 accuracy on 100 test articles, against 0.32 for always guessing the most common topic. Training took 20 seconds on cpu-basic.
    More recipes and options in uv-scripts/classification.
    
 
    
-
    You need the hf CLI (1.32 or newer), a login and pay-as-you-go credit. Add --dry-run to see the GPU and settings without starting a job.
    
+
    You need the hf CLI (1.32 or newer), a login and pay-as-you-go credit. Add --dry-run to see the GPU and settings without starting a job, and run hf jobs uv run --help for all options.
    
 
    Find your model
    
 
    Replace the capitalised placeholders and your-username. Check the script if you're unsure what a value should be.