serverless
minicpm-v46-strict-cycle-runpod-serverless
MiniCPM Strict Caption Harness
Strict 9-field cycling harness for MiniCPM-V-4.6 v2 captions. The harness asks the model for one field at a time, cleans each field, and assembles the final caption with deterministic v2 headers.
Smoke test without loading the model:
cd /Users/dustinpainter/datasets/image-datasets
PYTHONPATH=tools/mini-cap-harness python3 tools/mini-cap-harness/run_strict_cycle.py \
--backend mock \
--input… See the full description on the dataset page: https://huggingface.co/datasets/jaddai/minicpm-v46-strict-cycle-runpod-serverless.dev_mode-wtq
Dataset Card for dev_mode-wtq
Dataset Summary
The dev_mode-wtq dataset is a small-scale dataset for the task of question answering on semi-structured tables.
This data includes the aggregation_label and answer_coordinates to make it easy to train this model on any TAPAS based modles.
Supported Tasks and Leaderboards
question-answering, table-question-answering
Languages
en
Dataset Structure
Data Instances
default… See the full description on the dataset page: https://huggingface.co/datasets/Serverless/dev_mode-wtq.bon-prm-serverless-batchedrunpod_serverless_n1
serverless_n1: Ultravox + Kokoro TTS
Docker image and vLLM configuration for deploying Ultravox + Kokoro TTS on RunPod serverless.
Location: runpod_serverless_models/serverless_n1/
🎯 What This Does
Input: Audio or text
Processing: Ultravox v0.2 (8B speech-to-text-to-text)
Output: Text + synthesized audio (Kokoro TTS 82M)
Latency: ~0.3-0.5s warm inference
Cold Start: ~8-12 seconds
📁 Files
serverless_n1/
├── Dockerfile # Docker image definition… See the full description on the dataset page: https://huggingface.co/datasets/marcosremar2/runpod_serverless_n1.Catalyst_Serverless_Dataset