Instructions to use fickle1101/diffocr_ckpt10k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fickle1101/diffocr_ckpt10k with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="fickle1101/diffocr_ckpt10k", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("fickle1101/diffocr_ckpt10k", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fickle1101/diffocr_ckpt10k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fickle1101/diffocr_ckpt10k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fickle1101/diffocr_ckpt10k",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/fickle1101/diffocr_ckpt10k

SGLang

How to use fickle1101/diffocr_ckpt10k with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "fickle1101/diffocr_ckpt10k" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fickle1101/diffocr_ckpt10k",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "fickle1101/diffocr_ckpt10k" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fickle1101/diffocr_ckpt10k",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use fickle1101/diffocr_ckpt10k with Docker Model Runner:
```
docker model run hf.co/fickle1101/diffocr_ckpt10k
```

diffocr_ckpt10k

File size: 2,911 Bytes

764be1c

{
  "transformers_version": "5.9.0",
  "architectures": [
    "Qwen2VLDiffusionForConditionalGeneration"
  ],
  "dtype": "bfloat16",
  "text_config": {
    "architectures": [
      "Qwen2VLForConditionalGeneration"
    ],
    "dtype": "bfloat16",
    "vocab_size": 151936,
    "hidden_size": 896,
    "intermediate_size": 4864,
    "num_hidden_layers": 24,
    "num_attention_heads": 14,
    "num_key_value_heads": 2,
    "hidden_act": "silu",
    "max_position_embeddings": 8192,
    "initializer_range": 0.02,
    "rms_norm_eps": 1e-06,
    "use_cache": false,
    "use_sliding_window": false,
    "sliding_window": null,
    "max_window_layers": 24,
    "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"
    ],
    "attention_dropout": 0.0,
    "rope_parameters": {
      "mrope_section": [
        8,
        12,
        12
      ],
      "rope_type": "default",
      "type": "default",
      "rope_theta": 1000000.0
    },
    "bos_token_id": 151643,
    "eos_token_id": 151645,
    "pad_token_id": 151643,
    "tie_word_embeddings": true,
    "vision_token_id": 151654,
    "model_type": "qwen2_vl_text"
  },
  "vision_config": {
    "dtype": "bfloat16",
    "depth": 32,
    "embed_dim": 1280,
    "hidden_size": 896,
    "hidden_act": "quick_gelu",
    "mlp_ratio": 4,
    "num_heads": 16,
    "in_channels": 3,
    "patch_size": 14,
    "spatial_merge_size": 2,
    "temporal_patch_size": 2,
    "initializer_range": 0.02,
    "in_chans": 3,
    "pad_token_id": 151643,
    "spatial_patch_size": 14,
    "model_type": "qwen2_vl_vision"
  },
  "image_token_id": 151655,
  "video_token_id": 151656,
  "vision_start_token_id": 151652,
  "vision_end_token_id": 151653,
  "tie_word_embeddings": true,
  "model_type": "qwen2vl_diffusion",
  "vision_token_id": 151654,
  "auto_map": {
    "AutoConfig": "configuration_qwen2vl_diffusion.Qwen2VLDiffusionConfig",
    "AutoModel": "modeling_qwen2vl_diffusion.Qwen2VLDiffusionModel",
    "AutoModelForCausalLM": "modeling_qwen2vl_diffusion.Qwen2VLDiffusionForConditionalGeneration",
    "AutoModelForImageTextToText": "modeling_qwen2vl_diffusion.Qwen2VLDiffusionForConditionalGeneration"
  },
  "diffusion": {
    "mask_token": "<|mask|>",
    "mask_token_id": 151674,
    "block_size": 16,
    "denoising_steps": 16,
    "attention_mask_mode": "prefix_causal_block_full",
    "generation_mode": "block_diffusion"
  }
}