Instructions to use FelixKAI/UHR-BAT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FelixKAI/UHR-BAT with Transformers:

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

pipe = pipeline("image-text-to-text", model="FelixKAI/UHR-BAT", 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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("FelixKAI/UHR-BAT", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FelixKAI/UHR-BAT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FelixKAI/UHR-BAT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FelixKAI/UHR-BAT",
		"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/FelixKAI/UHR-BAT

SGLang

How to use FelixKAI/UHR-BAT 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 "FelixKAI/UHR-BAT" \
    --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": "FelixKAI/UHR-BAT",
		"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 "FelixKAI/UHR-BAT" \
        --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": "FelixKAI/UHR-BAT",
		"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 FelixKAI/UHR-BAT with Docker Model Runner:
```
docker model run hf.co/FelixKAI/UHR-BAT
```

UHR-BAT

File size: 2,094 Bytes

6b408dc

{
  "_name_or_path": "FelixKAI/UHR-BAT",
  "architectures": [
    "UHRBATForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "debug_print_token_counts": false,
  "enable_scale_pos_residual": true,
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "image_aspect_ratio": "pad",
  "image_crop_resolution": null,
  "image_grid_pinpoints": null,
  "image_split_resolution": null,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "max_position_embeddings": 224000,
  "max_window_layers": 28,
  "mm_hidden_size": 1024,
  "mm_patch_merge_type": "unires",
  "mm_projector_lr": null,
  "mm_projector_type": "mlp2x_gelu",
  "mm_resampler_type": null,
  "mm_spatial_pool_mode": "average",
  "mm_spatial_pool_stride": 2,
  "mm_tunable_parts": "mm_mlp_adapter,mm_language_model,scale_residuals",
  "mm_use_im_patch_token": false,
  "mm_use_im_start_end": false,
  "mm_vision_select_feature": "patch",
  "mm_vision_select_layer": -2,
  "mm_vision_tower": "openai/clip-vit-large-patch14-336",
  "mm_vision_tower_lr": null,
  "model_type": "uhr_bat",
  "multiscale_target_sizes": [
    672,
    1344,
    2688,
    4032
  ],
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "pos_skipping_range": 4096,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000000.0,
  "sam_checkpoint_path": null,
  "sam_keep_ratio": null,
  "sam_model_type": "vit_h",
  "sam_prune_ratio": 0.9,
  "sam_prune_target": 0,
  "scale_residual_base": 64,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "tokenizer_model_max_length": 20000,
  "tokenizer_padding_side": "right",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.43.4",
  "use_cache": true,
  "use_mm_proj": true,
  "use_pos_skipping": false,
  "use_sliding_window": false,
  "vision_tower_pretrained": null,
  "vocab_size": 152064,
  "auto_map": {
    "AutoConfig": "configuration_uhr_bat.UHRBATConfig",
    "AutoModelForCausalLM": "modeling_uhr_bat.UHRBATForCausalLM"
  },
  "library_name": "transformers",
  "trust_remote_code": true
}