Instructions to use shawnw3i/Hunyuan-MT-Chimera-7B-INT8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use shawnw3i/Hunyuan-MT-Chimera-7B-INT8 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="shawnw3i/Hunyuan-MT-Chimera-7B-INT8")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("shawnw3i/Hunyuan-MT-Chimera-7B-INT8") model = AutoModelForMultimodalLM.from_pretrained("shawnw3i/Hunyuan-MT-Chimera-7B-INT8") - Notebooks
- Google Colab
- Kaggle
| default_stage: | |
| default_modifiers: | |
| QuantizationModifier: | |
| targets: [Linear] | |
| ignore: ['re:.*embed_tokens.*', 're:.*lm_head.*'] | |
| scheme: W8A16 | |