Image-Text-to-Text
PEFT
Safetensors
laboratory
protocol-conditioned-action-prediction
lora
qwen
long-horizon-planning
conversational
Instructions to use Stanford-CongLab/LabHorizon-Model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Stanford-CongLab/LabHorizon-Model with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.6-35B-A3B") model = PeftModel.from_pretrained(base_model, "Stanford-CongLab/LabHorizon-Model") - Notebooks
- Google Colab
- Kaggle
| { | |
| "image_processor": { | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_processor_type": "Qwen2VLImageProcessor", | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "merge_size": 2, | |
| "patch_size": 16, | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "longest_edge": 16777216, | |
| "shortest_edge": 65536 | |
| }, | |
| "temporal_patch_size": 2 | |
| }, | |
| "processor_class": "Qwen3VLProcessor", | |
| "video_processor": { | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "do_sample_frames": true, | |
| "fps": 2, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "max_frames": 768, | |
| "merge_size": 2, | |
| "min_frames": 4, | |
| "patch_size": 16, | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "return_metadata": false, | |
| "size": { | |
| "longest_edge": 25165824, | |
| "shortest_edge": 4096 | |
| }, | |
| "temporal_patch_size": 2, | |
| "video_processor_type": "Qwen3VLVideoProcessor" | |
| } | |
| } | |