Translation
Transformers
Safetensors
multilingual
qwen3_5
image-text-to-text
instruction-following
wmt26
qwen3.5
Instructions to use WPS-Qingqiu/Qingqiu-MT-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use WPS-Qingqiu/Qingqiu-MT-9B with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="WPS-Qingqiu/Qingqiu-MT-9B")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("WPS-Qingqiu/Qingqiu-MT-9B") model = AutoModelForMultimodalLM.from_pretrained("WPS-Qingqiu/Qingqiu-MT-9B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "size": { | |
| "longest_edge": 16777216, | |
| "shortest_edge": 65536 | |
| }, | |
| "patch_size": 16, | |
| "temporal_patch_size": 2, | |
| "merge_size": 2, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "processor_class": "Qwen3VLProcessor", | |
| "image_processor_type": "Qwen2VLImageProcessorFast" | |
| } |