Image-Text-to-Text
Safetensors
ColPali
sauerkrautlm-colpali
qwen3_vl
document-retrieval
vision-language-model
multi-vector
late-interaction
visual-retrieval
qwen3-vl
mteb
vidore
Instructions to use VAGOsolutions/SauerkrautLM-ColQwen3-2b-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ColPali
How to use VAGOsolutions/SauerkrautLM-ColQwen3-2b-v0.1 with ColPali:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "ColQwen3" | |
| ], | |
| "base_model": "Qwen/Qwen3-VL-2B-Instruct", | |
| "dim": 128, | |
| "dtype": "float32", | |
| "image_token_id": 151655, | |
| "mask_non_image_embeddings": false, | |
| "model_type": "qwen3_vl", | |
| "text_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "dtype": "float32", | |
| "eos_token_id": 151645, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6144, | |
| "max_position_embeddings": 262144, | |
| "model_type": "qwen3_vl_text", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "mrope_interleaved": true, | |
| "mrope_section": [ | |
| 24, | |
| 20, | |
| 20 | |
| ], | |
| "rope_type": "default" | |
| }, | |
| "rope_theta": 5000000, | |
| "tie_word_embeddings": true, | |
| "use_cache": true, | |
| "vocab_size": 151936 | |
| }, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "4.57.1", | |
| "video_token_id": 151656, | |
| "vision_config": { | |
| "deepstack_visual_indexes": [ | |
| 5, | |
| 11, | |
| 17 | |
| ], | |
| "depth": 24, | |
| "dtype": "float32", | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1024, | |
| "in_channels": 3, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "model_type": "qwen3_vl", | |
| "num_heads": 16, | |
| "num_position_embeddings": 2304, | |
| "out_hidden_size": 2048, | |
| "patch_size": 16, | |
| "spatial_merge_size": 2, | |
| "temporal_patch_size": 2 | |
| }, | |
| "vision_end_token_id": 151653, | |
| "vision_start_token_id": 151652, | |
| "_name_or_path": "VAGOsolutions/SauerkrautLM-ColQwen3-2b-v0.1" | |
| } |