ranwakhaled/gemma-vl-exp1

Model Card for Model ID

Model Details

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

• Developed by: [More Information Needed]
• Funded by [optional]: [More Information Needed]
• Shared by [optional]: [More Information Needed]
• Model type: [More Information Needed]
• Language(s) (NLP): [More Information Needed]
• License: [More Information Needed]
• Finetuned from model [optional]: [More Information Needed]

Model Sources [optional]

• Repository: [More Information Needed]
• Paper [optional]: [More Information Needed]
• Demo [optional]: [More Information Needed]

Uses

Direct Use

[More Information Needed]

How to Get Started with the Model

import torch
from transformers import AutoProcessor, AutoModelForImageTextToText

# Select device
device = "cuda" if torch.cuda.is_available() else "cpu"

# Load model and processor
model = AutoModelForImageTextToText.from_pretrained(
    "ranwakhaled/gemma-vl-exp1",
    device_map=device
).eval()

processor = AutoProcessor.from_pretrained("ranwakhaled/gemma-vl-exp1")

# Example inputs
# - `image`: PIL image or tensor
# - `PROMPT`: text instruction
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": image},
            {"type": "text", "text": PROMPT},
        ],
    }
]

# Prepare inputs using chat template
inputs = processor.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
)

# Move inputs to the correct device
inputs = {k: v.to(model.device) for k, v in inputs.items()}

# Ensure image tensor matches model dtype (important for some GPUs)
if "pixel_values" in inputs:
    inputs["pixel_values"] = inputs["pixel_values"].to(model.dtype)

# Track input length to isolate generated tokens
input_length = inputs["input_ids"].shape[-1]

# Generate output
with torch.inference_mode():
    outputs = model.generate(
        **inputs,
        max_new_tokens=256,
        do_sample=False,
    )

# Remove prompt tokens from the generated sequence
generated_tokens = outputs[0][input_length:]

# Decode to text
decoded_output = processor.decode(
    generated_tokens,
    skip_special_tokens=True
)

print(decoded_output)

Training Details

Training Data

[More Information Needed]

Training Procedure

Training Hyperparameters

• Training regime: [More Information Needed]

Evaluation