Image-Text-to-Text
MLX
Safetensors
multilingual
internvl_chat
vision-language
ocr
document-intelligence
qianfan
apple-silicon
custom_code
Eval Results
4-bit precision
Instructions to use jason1966/Qianfan-OCR-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use jason1966/Qianfan-OCR-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("jason1966/Qianfan-OCR-MLX-4bit") config = load_config("jason1966/Qianfan-OCR-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": [ | |
| "InternVLChatModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_internvl_chat.InternVLChatConfig", | |
| "AutoModel": "modeling_internvl_chat.InternVLChatModel", | |
| "AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel" | |
| }, | |
| "downsample_ratio": 0.5, | |
| "dynamic_image_size": true, | |
| "eos_token_id": 151645, | |
| "force_image_size": 448, | |
| "llm_config": { | |
| "architectures": [ | |
| "Qwen3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "debug": false, | |
| "eos_token_id": 151645, | |
| "ep_size": 1, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2560, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 9728, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 36, | |
| "micro_forward": false, | |
| "model_type": "qwen3", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 5000000, | |
| "skip_checkpoint": false, | |
| "sliding_window": null, | |
| "torch_dtype": "bfloat16", | |
| "use_cache": false, | |
| "use_deepep": false, | |
| "use_sliding_window": false, | |
| "vocab_size": 153678 | |
| }, | |
| "max_dynamic_patch": 12, | |
| "min_dynamic_patch": 1, | |
| "model_type": "internvl_chat", | |
| "pad2square": false, | |
| "pad_token_id": 151643, | |
| "ps_version": "v2", | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "select_layer": -1, | |
| "template": "qianfanvl", | |
| "tie_word_embeddings": false, | |
| "transformers_version": null, | |
| "use_backbone_lora": 0, | |
| "use_llm_lora": 0, | |
| "use_thumbnail": true, | |
| "vision_config": { | |
| "architectures": [ | |
| "InternVisionModel" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_intern_vit.InternVisionConfig", | |
| "AutoModel": "modeling_intern_vit.InternVisionModel" | |
| }, | |
| "drop_path_rate": 0.1, | |
| "dropout": 0.0, | |
| "hidden_act": "gelu", | |
| "hidden_size": 1024, | |
| "image_size": 448, | |
| "initializer_factor": 1.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "layer_norm_eps": 1e-06, | |
| "model_type": "intern_vit_6b", | |
| "norm_type": "layer_norm", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 24, | |
| "patch_size": 14, | |
| "qk_normalization": false, | |
| "qkv_bias": true, | |
| "torch_dtype": "bfloat16", | |
| "use_fa3": false, | |
| "use_flash_attn": true | |
| } | |
| } |