Instructions to use zhibinlan/LLaVE-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zhibinlan/LLaVE-7B with Transformers:

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

pipe = pipeline("image-text-to-text", model="zhibinlan/LLaVE-7B")
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, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("zhibinlan/LLaVE-7B")
model = AutoModelForCausalLM.from_pretrained("zhibinlan/LLaVE-7B", 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 zhibinlan/LLaVE-7B with vLLM:

Install from pip and serve model

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

SGLang

How to use zhibinlan/LLaVE-7B 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 "zhibinlan/LLaVE-7B" \
    --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": "zhibinlan/LLaVE-7B",
		"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 "zhibinlan/LLaVE-7B" \
        --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": "zhibinlan/LLaVE-7B",
		"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 zhibinlan/LLaVE-7B with Docker Model Runner:
```
docker model run hf.co/zhibinlan/LLaVE-7B
```

zhibinlan commited on Mar 12, 2025

Commit

9d19d7e

verified ·

1 Parent(s): 30d11f9

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -12

README.md CHANGED Viewed

@@ -82,8 +82,7 @@ conv_template = "qwen_1_5"  # Make sure you use correct chat template for differ
 question = DEFAULT_IMAGE_TOKEN + " Represent the given image with the following question: What is in the image"
 conv = copy.deepcopy(conv_templates[conv_template])
 conv.append_message(conv.roles[0], question)
-conv.append_message(conv.roles[1], "
-")
 prompt_question = conv.get_prompt()
 input_ids = tokenizer_image_token(prompt_question, tokenizer, IMAGE_TOKEN_INDEX, return_tensors="pt").unsqueeze(0).to(device)
 attention_mask=input_ids.ne(tokenizer.pad_token_id)
@@ -93,8 +92,7 @@ query_embed = model.encode_multimodal_embeddings(input_ids, attention_mask=atten
 target_string = "A cat and a dog"
 conv = copy.deepcopy(conv_templates[conv_template])
 conv.append_message(conv.roles[0], target_string)
-conv.append_message(conv.roles[1], "
-")
 target_string = conv.get_prompt()
 target_input_ids = tokenizer(target_string, return_tensors="pt").input_ids.to(device)
 attention_mask=target_input_ids.ne(tokenizer.pad_token_id)
@@ -106,8 +104,7 @@ print("A cat and a dog similarity score: ", query_embed @ target_embed.T)
 neg_string = "A cat and a tiger"
 conv = copy.deepcopy(conv_templates[conv_template])
 conv.append_message(conv.roles[0], neg_string)
-conv.append_message(conv.roles[1], "
-")
 neg_string = conv.get_prompt()
 neg_input_ids = tokenizer(neg_string, return_tensors="pt").input_ids.to(device)
 attention_mask=neg_input_ids.ne(tokenizer.pad_token_id)
@@ -120,8 +117,7 @@ print("A cat and a tiger similarity score: ", query_embed @ neg_embed.T)
 pos_string = "Find me an everyday image that matches the given caption: A cat and a dog."
 conv = copy.deepcopy(conv_templates[conv_template])
 conv.append_message(conv.roles[0], pos_string)
-conv.append_message(conv.roles[1], "
-")
 pos_string = conv.get_prompt()
 pos_input_ids = tokenizer(pos_string, return_tensors="pt").input_ids.to(device)
 attention_mask=pos_input_ids.ne(tokenizer.pad_token_id)
@@ -130,8 +126,7 @@ pos_query_embed = model.encode_multimodal_embeddings(pos_input_ids, attention_ma
 target = DEFAULT_IMAGE_TOKEN + " Represent the given image."
 conv = copy.deepcopy(conv_templates[conv_template])
 conv.append_message(conv.roles[0], target)
-conv.append_message(conv.roles[1], "
-")
 prompt_target = conv.get_prompt()
 target_input_ids = tokenizer_image_token(prompt_target, tokenizer, IMAGE_TOKEN_INDEX, return_tensors="pt").unsqueeze(0).to(device)
 attention_mask=target_input_ids.ne(tokenizer.pad_token_id)
@@ -144,8 +139,7 @@ print("A cat and a dog image similarity score: ", pos_query_embed @ target_embed
 neg_string = "Find me an everyday image that matches the given caption: A cat and a tiger."
 conv = copy.deepcopy(conv_templates[conv_template])
 conv.append_message(conv.roles[0], neg_string)
-conv.append_message(conv.roles[1], "
-")
 neg_string = conv.get_prompt()
 neg_input_ids = tokenizer(neg_string, return_tensors="pt").input_ids.to(device)
 attention_mask=neg_input_ids.ne(tokenizer.pad_token_id)

 question = DEFAULT_IMAGE_TOKEN + " Represent the given image with the following question: What is in the image"
 conv = copy.deepcopy(conv_templates[conv_template])
 conv.append_message(conv.roles[0], question)
+conv.append_message(conv.roles[1], "\n")
 prompt_question = conv.get_prompt()
 input_ids = tokenizer_image_token(prompt_question, tokenizer, IMAGE_TOKEN_INDEX, return_tensors="pt").unsqueeze(0).to(device)
 attention_mask=input_ids.ne(tokenizer.pad_token_id)
 target_string = "A cat and a dog"
 conv = copy.deepcopy(conv_templates[conv_template])
 conv.append_message(conv.roles[0], target_string)
+conv.append_message(conv.roles[1], "\n")
 target_string = conv.get_prompt()
 target_input_ids = tokenizer(target_string, return_tensors="pt").input_ids.to(device)
 attention_mask=target_input_ids.ne(tokenizer.pad_token_id)
 neg_string = "A cat and a tiger"
 conv = copy.deepcopy(conv_templates[conv_template])
 conv.append_message(conv.roles[0], neg_string)
+conv.append_message(conv.roles[1], "\n")
 neg_string = conv.get_prompt()
 neg_input_ids = tokenizer(neg_string, return_tensors="pt").input_ids.to(device)
 attention_mask=neg_input_ids.ne(tokenizer.pad_token_id)
 pos_string = "Find me an everyday image that matches the given caption: A cat and a dog."
 conv = copy.deepcopy(conv_templates[conv_template])
 conv.append_message(conv.roles[0], pos_string)
+conv.append_message(conv.roles[1], "\n")
 pos_string = conv.get_prompt()
 pos_input_ids = tokenizer(pos_string, return_tensors="pt").input_ids.to(device)
 attention_mask=pos_input_ids.ne(tokenizer.pad_token_id)
 target = DEFAULT_IMAGE_TOKEN + " Represent the given image."
 conv = copy.deepcopy(conv_templates[conv_template])
 conv.append_message(conv.roles[0], target)
+conv.append_message(conv.roles[1], "\n")
 prompt_target = conv.get_prompt()
 target_input_ids = tokenizer_image_token(prompt_target, tokenizer, IMAGE_TOKEN_INDEX, return_tensors="pt").unsqueeze(0).to(device)
 attention_mask=target_input_ids.ne(tokenizer.pad_token_id)
 neg_string = "Find me an everyday image that matches the given caption: A cat and a tiger."
 conv = copy.deepcopy(conv_templates[conv_template])
 conv.append_message(conv.roles[0], neg_string)
+conv.append_message(conv.roles[1], "\n")
 neg_string = conv.get_prompt()
 neg_input_ids = tokenizer(neg_string, return_tensors="pt").input_ids.to(device)
 attention_mask=neg_input_ids.ne(tokenizer.pad_token_id)