Visual Question Answering
Transformers
Safetensors
cvrr_merged
feature-extraction
cvrr
custom_code
latent-reasoning
Instructions to use dmis-lab/InternVL3-9B-CVRR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dmis-lab/InternVL3-9B-CVRR with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="dmis-lab/InternVL3-9B-CVRR", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("dmis-lab/InternVL3-9B-CVRR", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "model_type": "cvrr_merged", | |
| "architectures": [ | |
| "CVRRMergedModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_cvrr_merged.CVRRMergedConfig", | |
| "AutoModel": "modeling_cvrr_merged.CVRRMergedModel", | |
| "AutoModelForImageTextToText": "modeling_cvrr_merged.CVRRMergedModel" | |
| }, | |
| "release": { | |
| "name": "CVRR-InternVL3-9B", | |
| "base_model": "OpenGVLab/InternVL3-9B", | |
| "ell_star": 35, | |
| "recurrent_layer": 36, | |
| "upper_decoder_start": 37, | |
| "inference_T": 4, | |
| "inference_beta": 0.33, | |
| "lora_rank": 32, | |
| "lora_alpha": 12.0, | |
| "lora_dropout": 0.01, | |
| "checkpoint_step": 500, | |
| "format": "cvrr_native_plus_merged_transition_v1", | |
| "merged_weight_dtype": "float32", | |
| "native_weight_bytes": 18277586944, | |
| "status": "gpu_vstar_comparison_completed", | |
| "upload_ready": true, | |
| "hub_model_id": "dmis-lab/InternVL3-9B-CVRR" | |
| } | |
| } | |