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
| { | |
| "do_sample": true, | |
| "eos_token_id": [ | |
| 127960, | |
| 127967 | |
| ], | |
| "pad_token_id": 127961, | |
| "repetition_penalty": 1.05, | |
| "temperature": 0.7, | |
| "top_k": 20, | |
| "top_p": 0.6, | |
| "transformers_version": "4.56.0" | |
| } | |