Instructions to use Suchae/eagle2-2b-trl-grpo-Multitask with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Suchae/eagle2-2b-trl-grpo-Multitask with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Suchae/eagle2-2b-trl-grpo-Multitask", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download processor_config.json from Suchae/eagle2-2b-trl-grpo-Multitask: direct link, hf CLI and curl.
- Browser
- Download file 528 Bytes
-
https://huggingface.co/Suchae/eagle2-2b-trl-grpo-Multitask/resolve/main/processor_config.json
- Command line
-
hf download hf://Suchae/eagle2-2b-trl-grpo-Multitask/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/Suchae/eagle2-2b-trl-grpo-Multitask/resolve/main/processor_config.json
528 Bytes
| { | |
| "auto_map": { | |
| "AutoImageProcessor": "nvidia/Eagle2-2B--image_processing_eagle2_5_vl_fast.Eagle2_5_VLImageProcessorFast", | |
| "AutoProcessor": "nvidia/Eagle2-2B--processing_eagle2_5_vl.Eagle2_5_VLProcessor" | |
| }, | |
| "image_end_token": "</img>", | |
| "image_placeholder": "image", | |
| "image_start_token": "<img>", | |
| "image_token": "<IMG_CONTEXT>", | |
| "processor_class": "Eagle2_5_VLProcessor", | |
| "tokens_per_tile": 256, | |
| "video_placeholder": "video", | |
| "video_token": "<IMG_CONTEXT>", | |
| "vision_feature_select_strategy": null | |
| } | |