Visual Document Retrieval
PEFT
Safetensors
vidore
multimodal_embedding
multilingual_embedding
Text-to-Visual Document (T→VD) retrieval
Instructions to use Metric-AI/ColQwenStella-2b-multilingual with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Metric-AI/ColQwenStella-2b-multilingual with PEFT:
from peft import PeftModel from transformers import AutoModel base_model = AutoModel.from_pretrained("Metric-AI/ColQwenStella-base-2b") model = PeftModel.from_pretrained(base_model, "Metric-AI/ColQwenStella-2b-multilingual") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from Metric-AI/ColQwenStella-2b-multilingual: direct link, hf CLI and curl.
- Browser
- Download file 670 Bytes
-
https://huggingface.co/Metric-AI/ColQwenStella-2b-multilingual/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://Metric-AI/ColQwenStella-2b-multilingual/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/Metric-AI/ColQwenStella-2b-multilingual/resolve/main/preprocessor_config.json
670 Bytes
| { | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.48145466, | |
| 0.4578275, | |
| 0.40821073 | |
| ], | |
| "image_processor_type": "Qwen2VLImageProcessor", | |
| "image_std": [ | |
| 0.26862954, | |
| 0.26130258, | |
| 0.27577711 | |
| ], | |
| "max_pixels": 12845056, | |
| "merge_size": 2, | |
| "min_pixels": 3136, | |
| "patch_size": 14, | |
| "processor_class": "ColQwenStellaProcessor", | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "longest_edge": 12845056, | |
| "shortest_edge": 3136 | |
| }, | |
| "temporal_patch_size": 2, | |
| "auto_map": { | |
| "AutoProcessor": "processing_colqwenstella.ColQwenStellaProcessor" | |
| } | |
| } | |