Instructions to use X-iZhang/libra-maira-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use X-iZhang/libra-maira-2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="X-iZhang/libra-maira-2", 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("X-iZhang/libra-maira-2", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use X-iZhang/libra-maira-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "X-iZhang/libra-maira-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "X-iZhang/libra-maira-2",
		"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/X-iZhang/libra-maira-2

SGLang

How to use X-iZhang/libra-maira-2 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 "X-iZhang/libra-maira-2" \
    --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": "X-iZhang/libra-maira-2",
		"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 "X-iZhang/libra-maira-2" \
        --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": "X-iZhang/libra-maira-2",
		"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 X-iZhang/libra-maira-2 with Docker Model Runner:
```
docker model run hf.co/X-iZhang/libra-maira-2
```

X-iZhang commited on Jul 16, 2025

Commit

88f2d2c

verified ·

1 Parent(s): 3e11f09

Update config.json

Browse files

Files changed (1) hide show

config.json +10 -5

config.json CHANGED Viewed

@@ -9,7 +9,7 @@
   "freeze_mm_mlp_adapter": false,
   "hidden_act": "silu",
   "hidden_size": 4096,
-  "image_aspect_ratio": "pad",
   "initializer_range": 0.02,
   "intermediate_size": 11008,
   "max_length": 4096,
@@ -22,7 +22,7 @@
   "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": "microsoft/rad-dino-maira-2",
   "model_type": "libra",
   "num_attention_heads": 32,
@@ -31,17 +31,22 @@
   "pad_token_id": 0,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "tokenizer_model_max_length": 1024,
   "tokenizer_padding_side": "right",
-  "torch_dtype": "float32",
   "transformers_version": "4.51.3",
   "tune_mm_mlp_adapter": true,
   "tune_mm_vision_resampler": false,
   "unfreeze_mm_vision_tower": true,
   "use_cache": false,
   "use_mm_proj": true,
   "vocab_size": 32207
-}

   "freeze_mm_mlp_adapter": false,
   "hidden_act": "silu",
   "hidden_size": 4096,
+  "image_aspect_ratio": "square",
   "initializer_range": 0.02,
   "intermediate_size": 11008,
   "max_length": 4096,
   "mm_use_im_patch_token": false,
   "mm_use_im_start_end": false,
   "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -1,
   "mm_vision_tower": "microsoft/rad-dino-maira-2",
   "model_type": "libra",
   "num_attention_heads": 32,
   "pad_token_id": 0,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+      "factor": 1.5,
+      "rope_type": "linear"
+    },
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "tokenizer_model_max_length": 1024,
   "tokenizer_padding_side": "right",
+  "torch_dtype": "float16",
   "transformers_version": "4.51.3",
+  "image_token_index": 32204,
   "tune_mm_mlp_adapter": true,
   "tune_mm_vision_resampler": false,
   "unfreeze_mm_vision_tower": true,
+  "use_maira_feature_norm": true,
   "use_cache": false,
   "use_mm_proj": true,
   "vocab_size": 32207
+}