Image-Text-to-Text
MLX
Safetensors
English
idefics3
text-generation
screen-parsing
ui-understanding
object-detection
grounding
web
screentag
docling
granite
quantized
apple-silicon
conversational
4-bit precision
Instructions to use olragon/ScreenVLM-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use olragon/ScreenVLM-MLX-4bit with MLX:
# Make sure mlx-vlm is installed # pip install --upgrade mlx-vlm from mlx_vlm import load, generate from mlx_vlm.prompt_utils import apply_chat_template from mlx_vlm.utils import load_config # Load the model model, processor = load("olragon/ScreenVLM-MLX-4bit") config = load_config("olragon/ScreenVLM-MLX-4bit") # Prepare input image = ["http://images.cocodataset.org/val2017/000000039769.jpg"] prompt = "Describe this image." # Apply chat template formatted_prompt = apply_chat_template( processor, config, prompt, num_images=1 ) # Generate output output = generate(model, processor, formatted_prompt, image) print(output) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "architectures": [ | |
| "Idefics3ForConditionalGeneration" | |
| ], | |
| "bos_token_id": 100264, | |
| "eos_token_id": 100257, | |
| "generation_config": { | |
| "_from_model_config": true, | |
| "bos_token_id": 100264, | |
| "eos_token_id": 100257, | |
| "pad_token_id": 100257, | |
| "transformers_version": "4.55.2", | |
| "use_cache": false | |
| }, | |
| "image_token_id": 100270, | |
| "model_type": "idefics3", | |
| "pad_token_id": 100257, | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "scale_factor": 4, | |
| "text_config": { | |
| "_name_or_path": "/proj/docling-vision/models/granitev06_hf_ai4k_sft_data_v5", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 100264, | |
| "eos_token_id": 100257, | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 576, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1536, | |
| "max_position_embeddings": 8192, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 9, | |
| "num_hidden_layers": 30, | |
| "num_key_value_heads": 3, | |
| "pad_token_id": 100257, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 100000.0, | |
| "torch_dtype": "bfloat16", | |
| "use_cache": false, | |
| "vocab_size": 100352 | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "4.55.2", | |
| "use_cache": true, | |
| "vision_config": { | |
| "attention_dropout": 0.0, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 768, | |
| "image_size": 512, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-06, | |
| "max_image_size": { | |
| "longest_edge": 512 | |
| }, | |
| "model_type": "idefics3_vision", | |
| "num_attention_heads": 12, | |
| "num_channels": 3, | |
| "num_hidden_layers": 12, | |
| "patch_size": 16, | |
| "size": { | |
| "longest_edge": 512 | |
| } | |
| }, | |
| "vocab_size": 100352 | |
| } |