Video-Text-to-Text
Transformers
Safetensors
English
qwen3_5
image-text-to-text
video
multimodal
video-captioning
temporal-grounding
qwen
text-generation
VLM
gptq
4-bit precision
quantized
custom_code
Instructions to use prasannaJagadesh/marlin-2B-GPTQ-4BITS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use prasannaJagadesh/marlin-2B-GPTQ-4BITS with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("prasannaJagadesh/marlin-2B-GPTQ-4BITS", trust_remote_code=True) model = AutoModelForMultimodalLM.from_pretrained("prasannaJagadesh/marlin-2B-GPTQ-4BITS", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "source_model": "/media/prasanna/716F26140AED9B67/models/Marlin-2B", | |
| "quantization": { | |
| "method": "gptq", | |
| "bits": 4, | |
| "group_size": 128, | |
| "desc_act": true, | |
| "sym": true | |
| }, | |
| "calibration_samples": 6, | |
| "note": "This directory was produced locally from the source checkpoint. The original checkpoint is unchanged." | |
| } |