Translation
Transformers
Safetensors
English
Thai
qwen3_5
image-text-to-text
thai
english
instruction-following
machine-translation
Instructions to use iapp/ChindaMT-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use iapp/ChindaMT-4B 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="iapp/ChindaMT-4B")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("iapp/ChindaMT-4B") model = AutoModelForMultimodalLM.from_pretrained("iapp/ChindaMT-4B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download generation_config.json from iapp/ChindaMT-4B: direct link, hf CLI and curl.
- Browser
- Download file 163 Bytes
-
https://huggingface.co/iapp/ChindaMT-4B/resolve/main/generation_config.json
- Command line
-
hf download hf://iapp/ChindaMT-4B/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/iapp/ChindaMT-4B/resolve/main/generation_config.json
163 Bytes
| { | |
| "_from_model_config": true, | |
| "eos_token_id": [ | |
| 248046, | |
| 248044 | |
| ], | |
| "pad_token_id": 248044, | |
| "transformers_version": "5.2.0", | |
| "use_cache": true | |
| } | |