Transformers
Safetensors
multi_modality
multimodal
kielgen-fast-mini
lora-merged
4-bit precision
16-bit
image understanding
text generation
image generation
Instructions to use kiel2/Kiel-Gen-2-Mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kiel2/Kiel-Gen-2-Mini with Transformers:
# Load model directly from transformers import MultiModalityCausalLM model = MultiModalityCausalLM.from_pretrained("kiel2/Kiel-Gen-2-Mini", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "add_special_token": false, | |
| "ignore_id": -100, | |
| "image_end_tag": "<end_of_image>", | |
| "image_processor": { | |
| "background_color": [ | |
| 127, | |
| 127, | |
| 127 | |
| ], | |
| "do_normalize": true, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_processor_type": "VLMImageProcessor", | |
| "image_size": 384, | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "min_size": 14, | |
| "rescale_factor": 0.00392156862745098 | |
| }, | |
| "image_start_tag": "<begin_of_image>", | |
| "image_tag": "<image_placeholder>", | |
| "mask_prompt": true, | |
| "num_image_tokens": 576, | |
| "pad_tag": "<\uff5c\u2581pad\u2581\uff5c>", | |
| "processor_class": "VLChatProcessor", | |
| "sft_format": "deepseek" | |
| } | |