Image-to-Text
Transformers
Safetensors
English
qwen2_vl
image-text-to-text
vision-language-model
document-understanding
handwritten-text
insurance-forms
vqa
phi-3.5-vision
lora
qlora
unsloth
medical-forms
ocr-free
Eval Results (legacy)
text-generation-inference
Instructions to use solvrays/mdf-form-reader-phi35-vision with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use solvrays/mdf-form-reader-phi35-vision with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="solvrays/mdf-form-reader-phi35-vision")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("solvrays/mdf-form-reader-phi35-vision") model = AutoModelForImageTextToText.from_pretrained("solvrays/mdf-form-reader-phi35-vision") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Unsloth Studio new
How to use solvrays/mdf-form-reader-phi35-vision with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for solvrays/mdf-form-reader-phi35-vision to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for solvrays/mdf-form-reader-phi35-vision to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for solvrays/mdf-form-reader-phi35-vision to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="solvrays/mdf-form-reader-phi35-vision", max_seq_length=2048, )
| { | |
| "architectures": [ | |
| "Qwen2VLForConditionalGeneration" | |
| ], | |
| "dtype": "bfloat16", | |
| "image_token_id": 151655, | |
| "model_name": "unsloth/qwen2-vl-7b-instruct", | |
| "model_type": "qwen2_vl", | |
| "pad_token_id": 151654, | |
| "text_config": { | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 3584, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18944, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 28, | |
| "model_type": "qwen2_vl_text", | |
| "num_attention_heads": 28, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 4, | |
| "pad_token_id": 151654, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "mrope_section": [ | |
| 16, | |
| 24, | |
| 24 | |
| ], | |
| "rope_theta": 1000000.0, | |
| "rope_type": "default", | |
| "type": "default" | |
| }, | |
| "sliding_window": null, | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 152064 | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.5.0", | |
| "unsloth_fixed": true, | |
| "unsloth_version": "2026.5.2", | |
| "video_token_id": 151656, | |
| "vision_config": { | |
| "depth": 32, | |
| "dtype": "bfloat16", | |
| "embed_dim": 1280, | |
| "hidden_act": "quick_gelu", | |
| "hidden_size": 3584, | |
| "in_channels": 3, | |
| "in_chans": 3, | |
| "initializer_range": 0.02, | |
| "mlp_ratio": 4, | |
| "model_type": "qwen2_vl", | |
| "num_heads": 16, | |
| "patch_size": 14, | |
| "spatial_merge_size": 2, | |
| "spatial_patch_size": 14, | |
| "temporal_patch_size": 2 | |
| }, | |
| "vision_end_token_id": 151653, | |
| "vision_start_token_id": 151652, | |
| "vision_token_id": 151654 | |
| } | |