Instructions to use prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF with Transformers:

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

pipe = pipeline("image-text-to-text", model="prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF")
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 AutoModel
model = AutoModel.from_pretrained("prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF", device_map="auto")

llama-cpp-python

How to use prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF",
	filename="OpenCaption-2B-VL-SFT-v1.0.BF16.gguf",
)

llm.create_chat_completion(
	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"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF:Q4_K_M

Use Docker

docker model run hf.co/prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF",
		"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/prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF:Q4_K_M

SGLang

How to use prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF 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 "prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF" \
    --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": "prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF",
		"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 "prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF" \
        --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": "prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF",
		"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"
						}
					}
				]
			}
		]
	}'

Ollama
How to use prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF:Q4_K_M
```

Unsloth Studio

How to use prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF:Q4_K_M
```

Lemonade

How to use prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/OpenCaption-2B-VL-SFT-v1.0-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.OpenCaption-2B-VL-SFT-v1.0-GGUF-Q4_K_M

List all available models

lemonade list

OpenCaption-2B-VL-SFT-v1.0-GGUF

OpenCaption-2B-VL-SFT-v1.0 is a vision-language captioning model built on top of Qwen/Qwen3-VL-2B-Instruct. It was trained for image captioning and high-quality dense image captioning using a fine-grained mixture of long-form image description traces. The model is designed to produce richer visual understanding than conventional captions by capturing scene composition, object relationships, spatial reasoning, attributes, actions, lighting, background context, and fine visual details.

This model is an experimental release and may produce unexpected outputs in some scenarios.

Model Files

File Name	Quant Type	File Size	File Link
OpenCaption-2B-VL-SFT-v1.0.BF16.gguf	BF16	3.45 GB	Download
OpenCaption-2B-VL-SFT-v1.0.F16.gguf	F16	3.45 GB	Download
OpenCaption-2B-VL-SFT-v1.0.F32.gguf	F32	6.89 GB	Download
OpenCaption-2B-VL-SFT-v1.0.Q3_K_L.gguf	Q3_K_L	1 GB	Download
OpenCaption-2B-VL-SFT-v1.0.Q3_K_M.gguf	Q3_K_M	940 MB	Download
OpenCaption-2B-VL-SFT-v1.0.Q3_K_S.gguf	Q3_K_S	867 MB	Download
OpenCaption-2B-VL-SFT-v1.0.Q4_0.gguf	Q4_0	1.05 GB	Download
OpenCaption-2B-VL-SFT-v1.0.Q4_K_M.gguf	Q4_K_M	1.11 GB	Download
OpenCaption-2B-VL-SFT-v1.0.Q4_K_S.gguf	Q4_K_S	1.06 GB	Download
OpenCaption-2B-VL-SFT-v1.0.Q5_0.gguf	Q5_0	1.23 GB	Download
OpenCaption-2B-VL-SFT-v1.0.Q5_K_M.gguf	Q5_K_M	1.26 GB	Download
OpenCaption-2B-VL-SFT-v1.0.Q5_K_S.gguf	Q5_K_S	1.23 GB	Download
OpenCaption-2B-VL-SFT-v1.0.Q6_K.gguf	Q6_K	1.42 GB	Download
OpenCaption-2B-VL-SFT-v1.0.Q8_0.gguf	Q8_0	1.83 GB	Download
OpenCaption-2B-VL-SFT-v1.0.mmproj-bf16.gguf	mmproj-bf16	823 MB	Download
OpenCaption-2B-VL-SFT-v1.0.mmproj-f16.gguf	mmproj-f16	823 MB	Download
OpenCaption-2B-VL-SFT-v1.0.mmproj-f32.gguf	mmproj-f32	1.63 GB	Download
OpenCaption-2B-VL-SFT-v1.0.mmproj-q8_0.gguf	mmproj-q8_0	445 MB	Download