Instructions to use CowCorpus/Cluster3-Takeover-Llava with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CowCorpus/Cluster3-Takeover-Llava with Transformers:

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

pipe = pipeline("text-generation", model="CowCorpus/Cluster3-Takeover-Llava")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("CowCorpus/Cluster3-Takeover-Llava")
model = AutoModelForImageTextToText.from_pretrained("CowCorpus/Cluster3-Takeover-Llava")
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

vLLM

How to use CowCorpus/Cluster3-Takeover-Llava with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CowCorpus/Cluster3-Takeover-Llava"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CowCorpus/Cluster3-Takeover-Llava",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CowCorpus/Cluster3-Takeover-Llava

SGLang

How to use CowCorpus/Cluster3-Takeover-Llava 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 "CowCorpus/Cluster3-Takeover-Llava" \
    --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": "CowCorpus/Cluster3-Takeover-Llava",
		"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 "CowCorpus/Cluster3-Takeover-Llava" \
        --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": "CowCorpus/Cluster3-Takeover-Llava",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CowCorpus/Cluster3-Takeover-Llava with Docker Model Runner:
```
docker model run hf.co/CowCorpus/Cluster3-Takeover-Llava
```

oaishi commited on Feb 9

Commit

57de309

verified ·

1 Parent(s): 6542e01

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -4

README.md CHANGED Viewed

@@ -20,7 +20,7 @@ metrics:
 library_name: transformers
 ---
-# Model Card for CowCorpus/UserGroup3_final_fixed_llava
 <!-- Provide a quick summary of what the model is/does. -->
 This model is a **specialized fine-tune** of the general [CowCorpus-Llava](https://huggingface.co/CowCorpus/CowCorpus-llama3-llava-next-8b) model.
@@ -56,14 +56,12 @@ The model is trained on a rich, multimodal state representation:
 For inference code, prompt templates, and setup instructions, please refer to our [GitHub Repository](https://github.com/oaishi/CowCorpus).
-## Training Details
 ### Training Data
 <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
 The model underwent a two-stage training process:
 1.  **Stage 1 (General Adaptation):** Fine-tuned on the complete CowCorpus dataset.
-2.  **Stage 2 (User Personalization):** Further fine-tuned on the **User Cluster 3 subset** of CowCorpus, consists of 26 trajectories and 131 steps. (P10, P13, P18)
 **User Cluster 2 Characteristics:**
 *   **Data Source:** A subset of the collaborative trajectories specific to User Group 3.

 library_name: transformers
 ---
+# Model Card for CowCorpus/Cluster3-Takeover-Llava
 <!-- Provide a quick summary of what the model is/does. -->
 This model is a **specialized fine-tune** of the general [CowCorpus-Llava](https://huggingface.co/CowCorpus/CowCorpus-llama3-llava-next-8b) model.
 For inference code, prompt templates, and setup instructions, please refer to our [GitHub Repository](https://github.com/oaishi/CowCorpus).
 ### Training Data
 <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
 The model underwent a two-stage training process:
 1.  **Stage 1 (General Adaptation):** Fine-tuned on the complete CowCorpus dataset.
+2.  **Stage 2 (User Personalization):** Further fine-tuned on the **User Cluster 3 subset** of CowCorpus, consists of 26 trajectories and 131 steps.
 **User Cluster 2 Characteristics:**
 *   **Data Source:** A subset of the collaborative trajectories specific to User Group 3.