colpali-v1.3-hf

Name: colpali-v1.3-hf
Author: vidore

2.3K

—

vidore

Other

OTHER

New

2K downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

Unknown

Mobile

Laptop

Server

Quick Summary

> [!IMPORTANT] > This version of ColPali should be loaded with the `transformers 🤗` release, not with `colpali-engine`. > It was converted using the `convertco...

Code Examples

Usagepythontransformers

import torch
from PIL import Image

from transformers import ColPaliForRetrieval, ColPaliProcessor

model_name = "vidore/colpali-v1.3-hf"

model = ColPaliForRetrieval.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="cuda:0",  # or "mps" if on Apple Silicon
).eval()

processor = ColPaliProcessor.from_pretrained(model_name)

# Your inputs
images = [
    Image.new("RGB", (32, 32), color="white"),
    Image.new("RGB", (16, 16), color="black"),
]
queries = [
    "What is the organizational structure for our R&D department?",
    "Can you provide a breakdown of last year’s financial performance?",
]

# Process the inputs
batch_images = processor(images=images).to(model.device)
batch_queries = processor(text=queries).to(model.device)

# Forward pass
with torch.no_grad():
    image_embeddings = model(**batch_images)
    query_embeddings = model(**batch_queries)

# Score the queries against the images
scores = processor.score_retrieval(query_embeddings.embeddings, image_embeddings.embeddings)

Usagepythontransformers

import torch
from PIL import Image

from transformers import ColPaliForRetrieval, ColPaliProcessor

model_name = "vidore/colpali-v1.3-hf"

model = ColPaliForRetrieval.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="cuda:0",  # or "mps" if on Apple Silicon
).eval()

processor = ColPaliProcessor.from_pretrained(model_name)

# Your inputs
images = [
    Image.new("RGB", (32, 32), color="white"),
    Image.new("RGB", (16, 16), color="black"),
]
queries = [
    "What is the organizational structure for our R&D department?",
    "Can you provide a breakdown of last year’s financial performance?",
]

# Process the inputs
batch_images = processor(images=images).to(model.device)
batch_queries = processor(text=queries).to(model.device)

# Forward pass
with torch.no_grad():
    image_embeddings = model(**batch_images)
    query_embeddings = model(**batch_queries)

# Score the queries against the images
scores = processor.score_retrieval(query_embeddings.embeddings, image_embeddings.embeddings)

Usagepythontransformers

import torch
from PIL import Image

from transformers import ColPaliForRetrieval, ColPaliProcessor

model_name = "vidore/colpali-v1.3-hf"

model = ColPaliForRetrieval.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="cuda:0",  # or "mps" if on Apple Silicon
).eval()

processor = ColPaliProcessor.from_pretrained(model_name)

# Your inputs
images = [
    Image.new("RGB", (32, 32), color="white"),
    Image.new("RGB", (16, 16), color="black"),
]
queries = [
    "What is the organizational structure for our R&D department?",
    "Can you provide a breakdown of last year’s financial performance?",
]

# Process the inputs
batch_images = processor(images=images).to(model.device)
batch_queries = processor(text=queries).to(model.device)

# Forward pass
with torch.no_grad():
    image_embeddings = model(**batch_images)
    query_embeddings = model(**batch_queries)

# Score the queries against the images
scores = processor.score_retrieval(query_embeddings.embeddings, image_embeddings.embeddings)

Usagepythontransformers

import torch
from PIL import Image

from transformers import ColPaliForRetrieval, ColPaliProcessor

model_name = "vidore/colpali-v1.3-hf"

model = ColPaliForRetrieval.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="cuda:0",  # or "mps" if on Apple Silicon
).eval()

processor = ColPaliProcessor.from_pretrained(model_name)

# Your inputs
images = [
    Image.new("RGB", (32, 32), color="white"),
    Image.new("RGB", (16, 16), color="black"),
]
queries = [
    "What is the organizational structure for our R&D department?",
    "Can you provide a breakdown of last year’s financial performance?",
]

# Process the inputs
batch_images = processor(images=images).to(model.device)
batch_queries = processor(text=queries).to(model.device)

# Forward pass
with torch.no_grad():
    image_embeddings = model(**batch_images)
    query_embeddings = model(**batch_queries)

# Score the queries against the images
scores = processor.score_retrieval(query_embeddings.embeddings, image_embeddings.embeddings)

Usagepythontransformers

import torch
from PIL import Image

from transformers import ColPaliForRetrieval, ColPaliProcessor

model_name = "vidore/colpali-v1.3-hf"

model = ColPaliForRetrieval.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="cuda:0",  # or "mps" if on Apple Silicon
).eval()

processor = ColPaliProcessor.from_pretrained(model_name)

# Your inputs
images = [
    Image.new("RGB", (32, 32), color="white"),
    Image.new("RGB", (16, 16), color="black"),
]
queries = [
    "What is the organizational structure for our R&D department?",
    "Can you provide a breakdown of last year’s financial performance?",
]

# Process the inputs
batch_images = processor(images=images).to(model.device)
batch_queries = processor(text=queries).to(model.device)

# Forward pass
with torch.no_grad():
    image_embeddings = model(**batch_images)
    query_embeddings = model(**batch_queries)

# Score the queries against the images
scores = processor.score_retrieval(query_embeddings.embeddings, image_embeddings.embeddings)

Usagepythontransformers

import torch
from PIL import Image

from transformers import ColPaliForRetrieval, ColPaliProcessor

model_name = "vidore/colpali-v1.3-hf"

model = ColPaliForRetrieval.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="cuda:0",  # or "mps" if on Apple Silicon
).eval()

processor = ColPaliProcessor.from_pretrained(model_name)

# Your inputs
images = [
    Image.new("RGB", (32, 32), color="white"),
    Image.new("RGB", (16, 16), color="black"),
]
queries = [
    "What is the organizational structure for our R&D department?",
    "Can you provide a breakdown of last year’s financial performance?",
]

# Process the inputs
batch_images = processor(images=images).to(model.device)
batch_queries = processor(text=queries).to(model.device)

# Forward pass
with torch.no_grad():
    image_embeddings = model(**batch_images)
    query_embeddings = model(**batch_queries)

# Score the queries against the images
scores = processor.score_retrieval(query_embeddings.embeddings, image_embeddings.embeddings)

Usagepythontransformers

import torch
from PIL import Image

from transformers import ColPaliForRetrieval, ColPaliProcessor

model_name = "vidore/colpali-v1.3-hf"

model = ColPaliForRetrieval.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="cuda:0",  # or "mps" if on Apple Silicon
).eval()

processor = ColPaliProcessor.from_pretrained(model_name)

# Your inputs
images = [
    Image.new("RGB", (32, 32), color="white"),
    Image.new("RGB", (16, 16), color="black"),
]
queries = [
    "What is the organizational structure for our R&D department?",
    "Can you provide a breakdown of last year’s financial performance?",
]

# Process the inputs
batch_images = processor(images=images).to(model.device)
batch_queries = processor(text=queries).to(model.device)

# Forward pass
with torch.no_grad():
    image_embeddings = model(**batch_images)
    query_embeddings = model(**batch_queries)

# Score the queries against the images
scores = processor.score_retrieval(query_embeddings.embeddings, image_embeddings.embeddings)

Usagepythontransformers

import torch
from PIL import Image

from transformers import ColPaliForRetrieval, ColPaliProcessor

model_name = "vidore/colpali-v1.3-hf"

model = ColPaliForRetrieval.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="cuda:0",  # or "mps" if on Apple Silicon
).eval()

processor = ColPaliProcessor.from_pretrained(model_name)

# Your inputs
images = [
    Image.new("RGB", (32, 32), color="white"),
    Image.new("RGB", (16, 16), color="black"),
]
queries = [
    "What is the organizational structure for our R&D department?",
    "Can you provide a breakdown of last year’s financial performance?",
]

# Process the inputs
batch_images = processor(images=images).to(model.device)
batch_queries = processor(text=queries).to(model.device)

# Forward pass
with torch.no_grad():
    image_embeddings = model(**batch_images)
    query_embeddings = model(**batch_queries)

# Score the queries against the images
scores = processor.score_retrieval(query_embeddings.embeddings, image_embeddings.embeddings)

Usagepythontransformers

import torch
from PIL import Image

from transformers import ColPaliForRetrieval, ColPaliProcessor

model_name = "vidore/colpali-v1.3-hf"

model = ColPaliForRetrieval.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="cuda:0",  # or "mps" if on Apple Silicon
).eval()

processor = ColPaliProcessor.from_pretrained(model_name)

# Your inputs
images = [
    Image.new("RGB", (32, 32), color="white"),
    Image.new("RGB", (16, 16), color="black"),
]
queries = [
    "What is the organizational structure for our R&D department?",
    "Can you provide a breakdown of last year’s financial performance?",
]

# Process the inputs
batch_images = processor(images=images).to(model.device)
batch_queries = processor(text=queries).to(model.device)

# Forward pass
with torch.no_grad():
    image_embeddings = model(**batch_images)
    query_embeddings = model(**batch_queries)

# Score the queries against the images
scores = processor.score_retrieval(query_embeddings.embeddings, image_embeddings.embeddings)

Usagepythontransformers

import torch
from PIL import Image

from transformers import ColPaliForRetrieval, ColPaliProcessor

model_name = "vidore/colpali-v1.3-hf"

model = ColPaliForRetrieval.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="cuda:0",  # or "mps" if on Apple Silicon
).eval()

processor = ColPaliProcessor.from_pretrained(model_name)

# Your inputs
images = [
    Image.new("RGB", (32, 32), color="white"),
    Image.new("RGB", (16, 16), color="black"),
]
queries = [
    "What is the organizational structure for our R&D department?",
    "Can you provide a breakdown of last year’s financial performance?",
]

# Process the inputs
batch_images = processor(images=images).to(model.device)
batch_queries = processor(text=queries).to(model.device)

# Forward pass
with torch.no_grad():
    image_embeddings = model(**batch_images)
    query_embeddings = model(**batch_queries)

# Score the queries against the images
scores = processor.score_retrieval(query_embeddings.embeddings, image_embeddings.embeddings)

Usagepythontransformers

import torch
from PIL import Image

from transformers import ColPaliForRetrieval, ColPaliProcessor

model_name = "vidore/colpali-v1.3-hf"

model = ColPaliForRetrieval.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="cuda:0",  # or "mps" if on Apple Silicon
).eval()

processor = ColPaliProcessor.from_pretrained(model_name)

# Your inputs
images = [
    Image.new("RGB", (32, 32), color="white"),
    Image.new("RGB", (16, 16), color="black"),
]
queries = [
    "What is the organizational structure for our R&D department?",
    "Can you provide a breakdown of last year’s financial performance?",
]

# Process the inputs
batch_images = processor(images=images).to(model.device)
batch_queries = processor(text=queries).to(model.device)

# Forward pass
with torch.no_grad():
    image_embeddings = model(**batch_images)
    query_embeddings = model(**batch_queries)

# Score the queries against the images
scores = processor.score_retrieval(query_embeddings.embeddings, image_embeddings.embeddings)

Usagepythontransformers

import torch
from PIL import Image

from transformers import ColPaliForRetrieval, ColPaliProcessor

model_name = "vidore/colpali-v1.3-hf"

model = ColPaliForRetrieval.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="cuda:0",  # or "mps" if on Apple Silicon
).eval()

processor = ColPaliProcessor.from_pretrained(model_name)

# Your inputs
images = [
    Image.new("RGB", (32, 32), color="white"),
    Image.new("RGB", (16, 16), color="black"),
]
queries = [
    "What is the organizational structure for our R&D department?",
    "Can you provide a breakdown of last year’s financial performance?",
]

# Process the inputs
batch_images = processor(images=images).to(model.device)
batch_queries = processor(text=queries).to(model.device)

# Forward pass
with torch.no_grad():
    image_embeddings = model(**batch_images)
    query_embeddings = model(**batch_queries)

# Score the queries against the images
scores = processor.score_retrieval(query_embeddings.embeddings, image_embeddings.embeddings)

Usagepythontransformers

import torch
from PIL import Image

from transformers import ColPaliForRetrieval, ColPaliProcessor

model_name = "vidore/colpali-v1.3-hf"

model = ColPaliForRetrieval.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="cuda:0",  # or "mps" if on Apple Silicon
).eval()

processor = ColPaliProcessor.from_pretrained(model_name)

# Your inputs
images = [
    Image.new("RGB", (32, 32), color="white"),
    Image.new("RGB", (16, 16), color="black"),
]
queries = [
    "What is the organizational structure for our R&D department?",
    "Can you provide a breakdown of last year’s financial performance?",
]

# Process the inputs
batch_images = processor(images=images).to(model.device)
batch_queries = processor(text=queries).to(model.device)

# Forward pass
with torch.no_grad():
    image_embeddings = model(**batch_images)
    query_embeddings = model(**batch_queries)

# Score the queries against the images
scores = processor.score_retrieval(query_embeddings.embeddings, image_embeddings.embeddings)

Usagepythontransformers

import torch
from PIL import Image

from transformers import ColPaliForRetrieval, ColPaliProcessor

model_name = "vidore/colpali-v1.3-hf"

model = ColPaliForRetrieval.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="cuda:0",  # or "mps" if on Apple Silicon
).eval()

processor = ColPaliProcessor.from_pretrained(model_name)

# Your inputs
images = [
    Image.new("RGB", (32, 32), color="white"),
    Image.new("RGB", (16, 16), color="black"),
]
queries = [
    "What is the organizational structure for our R&D department?",
    "Can you provide a breakdown of last year’s financial performance?",
]

# Process the inputs
batch_images = processor(images=images).to(model.device)
batch_queries = processor(text=queries).to(model.device)

# Forward pass
with torch.no_grad():
    image_embeddings = model(**batch_images)
    query_embeddings = model(**batch_queries)

# Score the queries against the images
scores = processor.score_retrieval(query_embeddings.embeddings, image_embeddings.embeddings)

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.