Instructions to use llava-hf/llava-onevision-qwen2-7b-ov-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llava-hf/llava-onevision-qwen2-7b-ov-hf with Transformers:

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

pipe = pipeline("image-text-to-text", model="llava-hf/llava-onevision-qwen2-7b-ov-hf")
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("llava-hf/llava-onevision-qwen2-7b-ov-hf")
model = AutoModelForMultimodalLM.from_pretrained("llava-hf/llava-onevision-qwen2-7b-ov-hf", 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 llava-hf/llava-onevision-qwen2-7b-ov-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "llava-hf/llava-onevision-qwen2-7b-ov-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "llava-hf/llava-onevision-qwen2-7b-ov-hf",
		"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/llava-hf/llava-onevision-qwen2-7b-ov-hf

SGLang

How to use llava-hf/llava-onevision-qwen2-7b-ov-hf 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 "llava-hf/llava-onevision-qwen2-7b-ov-hf" \
    --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": "llava-hf/llava-onevision-qwen2-7b-ov-hf",
		"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 "llava-hf/llava-onevision-qwen2-7b-ov-hf" \
        --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": "llava-hf/llava-onevision-qwen2-7b-ov-hf",
		"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 llava-hf/llava-onevision-qwen2-7b-ov-hf with Docker Model Runner:
```
docker model run hf.co/llava-hf/llava-onevision-qwen2-7b-ov-hf
```

RaushanTurganbay HF Staff commited on Aug 15, 2024

Commit

bd59bb6

verified ·

1 Parent(s): 319e304

Upload LlavaOnevisionForConditionalGeneration

Browse files

Files changed (3) hide show

config.json +4 -9
model-00001-of-00004.safetensors +1 -1
model-00004-of-00004.safetensors +1 -1

config.json CHANGED Viewed

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "/raid/raushan/ov-7b",
   "architectures": [
-    "LlavaNextForConditionalGeneration"
   ],
   "ignore_index": -100,
   "image_grid_pinpoints": [
@@ -151,7 +151,7 @@
     ]
   ],
   "image_token_index": 151646,
-  "model_type": "llava_next",
   "projector_hidden_act": "gelu",
   "text_config": {
     "_name_or_path": "Qwen/Qwen2-7B-Instruct",
@@ -162,29 +162,24 @@
     "eos_token_id": 151645,
     "hidden_size": 3584,
     "intermediate_size": 18944,
-    "max_position_embeddings": 32768,
-    "max_window_layers": 28,
     "model_type": "qwen2",
     "num_attention_heads": 28,
     "num_hidden_layers": 28,
     "num_key_value_heads": 4,
     "rope_theta": 1000000.0,
-    "sliding_window": null,
     "torch_dtype": "bfloat16",
-    "use_sliding_window": false,
     "vocab_size": 152128
   },
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.45.0.dev0",
   "use_image_newline_parameter": true,
   "vision_aspect_ratio": "anyres_max_9",
   "vision_config": {
-    "hidden_act": "gelu_pytorch_tanh",
     "hidden_size": 1152,
     "image_size": 384,
     "intermediate_size": 4304,
-    "layer_norm_eps": 1e-06,
     "model_type": "siglip_vision_model",
     "num_attention_heads": 16,
     "num_hidden_layers": 26,

 {
+  "_name_or_path": "/raid/raushan/si-7b",
   "architectures": [
+    "LlavaOnevisionForConditionalGeneration"
   ],
   "ignore_index": -100,
   "image_grid_pinpoints": [
     ]
   ],
   "image_token_index": 151646,
+  "model_type": "llava_onevision",
   "projector_hidden_act": "gelu",
   "text_config": {
     "_name_or_path": "Qwen/Qwen2-7B-Instruct",
     "eos_token_id": 151645,
     "hidden_size": 3584,
     "intermediate_size": 18944,
     "model_type": "qwen2",
     "num_attention_heads": 28,
     "num_hidden_layers": 28,
     "num_key_value_heads": 4,
     "rope_theta": 1000000.0,
     "torch_dtype": "bfloat16",
     "vocab_size": 152128
   },
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.45.0.dev0",
   "use_image_newline_parameter": true,
+  "video_token_index": 151647,
   "vision_aspect_ratio": "anyres_max_9",
   "vision_config": {
     "hidden_size": 1152,
     "image_size": 384,
     "intermediate_size": 4304,
     "model_type": "siglip_vision_model",
     "num_attention_heads": 16,
     "num_hidden_layers": 26,

model-00001-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf7993771c8a5d9e67031d4ee564de16af03149c94a41fb022b7f837cbff2929
 size 4911200360

 version https://git-lfs.github.com/spec/v1
+oid sha256:ad4cb27d2a3f6e987147619cf2508a5bbb1b6b4c2d5533501fcc4a287a90e5af
 size 4911200360

model-00004-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:648b3aad9870352447111467fbae2393c5482c492f9cbc7f99c7d21b0a3ff9f2
 size 1226266240

 version https://git-lfs.github.com/spec/v1
+oid sha256:a2d1e40e47e9b524efcbbcab68e97fe4e7aadfe9a51bc14b54cc2331c48ebff6
 size 1226266240