Instructions to use Nayana-cognitivelab/NayanaEmbed-ColGemma3-Merge-Colbert-base-nayana-linear with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nayana-cognitivelab/NayanaEmbed-ColGemma3-Merge-Colbert-base-nayana-linear with Transformers:

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

pipe = pipeline("image-text-to-text", model="Nayana-cognitivelab/NayanaEmbed-ColGemma3-Merge-Colbert-base-nayana-linear")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Nayana-cognitivelab/NayanaEmbed-ColGemma3-Merge-Colbert-base-nayana-linear", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Nayana-cognitivelab/NayanaEmbed-ColGemma3-Merge-Colbert-base-nayana-linear with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nayana-cognitivelab/NayanaEmbed-ColGemma3-Merge-Colbert-base-nayana-linear"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nayana-cognitivelab/NayanaEmbed-ColGemma3-Merge-Colbert-base-nayana-linear",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Nayana-cognitivelab/NayanaEmbed-ColGemma3-Merge-Colbert-base-nayana-linear

SGLang

How to use Nayana-cognitivelab/NayanaEmbed-ColGemma3-Merge-Colbert-base-nayana-linear 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 "Nayana-cognitivelab/NayanaEmbed-ColGemma3-Merge-Colbert-base-nayana-linear" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nayana-cognitivelab/NayanaEmbed-ColGemma3-Merge-Colbert-base-nayana-linear",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Nayana-cognitivelab/NayanaEmbed-ColGemma3-Merge-Colbert-base-nayana-linear" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nayana-cognitivelab/NayanaEmbed-ColGemma3-Merge-Colbert-base-nayana-linear",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Nayana-cognitivelab/NayanaEmbed-ColGemma3-Merge-Colbert-base-nayana-linear with Docker Model Runner:
```
docker model run hf.co/Nayana-cognitivelab/NayanaEmbed-ColGemma3-Merge-Colbert-base-nayana-linear
```

Merged ColGemma3 Model

This model is a merged version of multiple ColGemma3 models using the linear merging technique.

Source Models

Merge Method: LINEAR

Linear interpolation: Weighted average of model parameters.

Model Architecture

ColGemma3 is a vision-language model for late interaction retrieval:

Base: Gemma3 vision-language model
Vision Encoder: Processes images into patch embeddings
Custom Projection: Projects embeddings to 128 dimensions
Retrieval: Uses MaxSim scoring for multi-vector retrieval

Usage

from colpali_engine.models.gemma3.colgemma3 import ColGemma3, ColGemmaProcessor3
from PIL import Image
import torch

# Load model and processor
model = ColGemma3.from_pretrained("Nayana-cognitivelab/NayanaEmbed-ColGemma3-Merge-Colbert-base-nayana-linear", torch_dtype=torch.bfloat16, device_map="auto")
processor = ColGemmaProcessor3.from_pretrained("Nayana-cognitivelab/NayanaEmbed-ColGemma3-Merge-Colbert-base-nayana-linear")

# Process images
images = [Image.open("document.png")]
batch_images = processor.process_images(images).to(model.device)

# Process queries
queries = ["What is this document about?"]
batch_queries = processor.process_queries(queries).to(model.device)

# Generate embeddings
with torch.no_grad():
    img_embeddings = model(**batch_images)
    query_embeddings = model(**batch_queries)

# Compute similarity scores
scores = processor.score([query_embeddings[0]], [img_embeddings[0]])

Citation

If you use this model, please cite the original ColGemma3 work and the source models.

This model was automatically merged using Modal infrastructure.

Downloads last month: 2

Safetensors

Model size

4B params

Tensor type

BF16

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support