Instructions to use lamm-mit/Graph-PRefLexOR-4B-Inpainting with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lamm-mit/Graph-PRefLexOR-4B-Inpainting with Transformers:

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

pipe = pipeline("text-generation", model="lamm-mit/Graph-PRefLexOR-4B-Inpainting")
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 AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("lamm-mit/Graph-PRefLexOR-4B-Inpainting")
model = AutoModelForMultimodalLM.from_pretrained("lamm-mit/Graph-PRefLexOR-4B-Inpainting", device_map="auto")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lamm-mit/Graph-PRefLexOR-4B-Inpainting with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lamm-mit/Graph-PRefLexOR-4B-Inpainting"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lamm-mit/Graph-PRefLexOR-4B-Inpainting",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lamm-mit/Graph-PRefLexOR-4B-Inpainting

SGLang

How to use lamm-mit/Graph-PRefLexOR-4B-Inpainting 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 "lamm-mit/Graph-PRefLexOR-4B-Inpainting" \
    --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": "lamm-mit/Graph-PRefLexOR-4B-Inpainting",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "lamm-mit/Graph-PRefLexOR-4B-Inpainting" \
        --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": "lamm-mit/Graph-PRefLexOR-4B-Inpainting",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lamm-mit/Graph-PRefLexOR-4B-Inpainting with Docker Model Runner:
```
docker model run hf.co/lamm-mit/Graph-PRefLexOR-4B-Inpainting
```

Graph-PRefLexOR-4B-Inpainting

File size: 5,176 Bytes

3934b7a

{
  "architectures": [
    "Gemma4ForConditionalGeneration"
  ],
  "audio_config": {
    "_name_or_path": "",
    "architectures": null,
    "attention_chunk_size": 12,
    "attention_context_left": 13,
    "attention_context_right": 0,
    "attention_invalid_logits_value": -1000000000.0,
    "attention_logit_cap": 50.0,
    "chunk_size_feed_forward": 0,
    "conv_kernel_size": 5,
    "dtype": "bfloat16",
    "gradient_clipping": 10000000000.0,
    "hidden_act": "silu",
    "hidden_size": 1024,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "model_type": "gemma4_audio",
    "num_attention_heads": 8,
    "num_hidden_layers": 12,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_proj_dims": 1536,
    "problem_type": null,
    "residual_weight": 0.5,
    "return_dict": true,
    "rms_norm_eps": 1e-06,
    "subsampling_conv_channels": [
      128,
      32
    ],
    "use_clipped_linears": true
  },
  "audio_token_id": 258881,
  "boa_token_id": 256000,
  "boi_token_id": 255999,
  "dtype": "bfloat16",
  "eoa_token_id": 258883,
  "eoa_token_index": 258883,
  "eoi_token_id": 258882,
  "eos_token_id": [
    1,
    106
  ],
  "image_token_id": 258880,
  "initializer_range": 0.02,
  "model_type": "gemma4",
  "text_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "attention_k_eq_v": false,
    "bos_token_id": 2,
    "dtype": "bfloat16",
    "enable_moe_block": false,
    "eos_token_id": 1,
    "expert_intermediate_size": null,
    "final_logit_softcapping": 30.0,
    "global_head_dim": 512,
    "head_dim": 256,
    "hidden_activation": "gelu_pytorch_tanh",
    "hidden_size": 2560,
    "hidden_size_per_layer_input": 256,
    "initializer_range": 0.02,
    "intermediate_size": 10240,
    "layer_types": [
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention"
    ],
    "max_position_embeddings": 131072,
    "model_type": "gemma4_text",
    "moe_intermediate_size": null,
    "num_attention_heads": 8,
    "num_experts": null,
    "num_global_key_value_heads": null,
    "num_hidden_layers": 42,
    "num_key_value_heads": 2,
    "num_kv_shared_layers": 18,
    "pad_token_id": 0,
    "rms_norm_eps": 1e-06,
    "rope_parameters": {
      "full_attention": {
        "partial_rotary_factor": 0.25,
        "rope_theta": 1000000.0,
        "rope_type": "proportional"
      },
      "sliding_attention": {
        "rope_theta": 10000.0,
        "rope_type": "default"
      }
    },
    "sliding_window": 512,
    "tie_word_embeddings": true,
    "top_k_experts": null,
    "use_bidirectional_attention": null,
    "use_cache": true,
    "use_double_wide_mlp": false,
    "vocab_size": 262144,
    "vocab_size_per_layer_input": 262144
  },
  "tie_word_embeddings": true,
  "transformers_version": "5.13.1",
  "video_token_id": 258884,
  "vision_config": {
    "_name_or_path": "",
    "architectures": null,
    "attention_bias": false,
    "attention_dropout": 0.0,
    "chunk_size_feed_forward": 0,
    "default_output_length": 280,
    "dtype": "bfloat16",
    "global_head_dim": 64,
    "head_dim": 64,
    "hidden_activation": "gelu_pytorch_tanh",
    "hidden_size": 768,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "max_position_embeddings": 131072,
    "model_type": "gemma4_vision",
    "num_attention_heads": 12,
    "num_hidden_layers": 16,
    "num_key_value_heads": 12,
    "output_attentions": false,
    "output_hidden_states": false,
    "patch_size": 16,
    "pooling_kernel_size": 3,
    "position_embedding_size": 10240,
    "problem_type": null,
    "return_dict": true,
    "rms_norm_eps": 1e-06,
    "rope_parameters": {
      "rope_theta": 100.0,
      "rope_type": "default"
    },
    "standardize": false,
    "use_clipped_linears": true
  },
  "vision_soft_tokens_per_image": 280
}