Google Gemma 3 27b It Text

🚀 Gemma 3 Text-Only Model Card

This is a text-only version of the Gemma 3 model, adapted from Google's original multimodal Gemma 3. It's more lightweight and suitable for text-only processing.

🚀 Quick Start

The following is a basic usage example of the Gemma 3 text-only model:

from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "your-username/gemma-3-27b-text" # Replace with your model path after uploading
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

messages = [
    {"role": "system", "content": "You are an AI assistant that provides helpful and accurate information."},
    {"role": "user", "content": "Hello. How's the weather today?"}
]

inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
)

outputs = model.generate(
    inputs,
    max_new_tokens=512,
    temperature=0.2,
    do_sample=True
)

response = tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True)
print(response)

✨ Features

• Text-only Adaptation: Adapted from Google's original multimodal Gemma 3, with image processing capabilities removed while preserving text generation capabilities.
• Large Context Window: Maintains a 128K context window, enabling handling of long - text inputs.
• Multilingual Support: Supports over 140 languages, suitable for a wide range of text generation tasks.
• Lightweight and Practical: More lightweight and suitable for environments where only text processing is needed or where resource constraints make the full multimodal model impractical.

📚 Documentation

Model Information

• Original Model: Gemma 3 by Google DeepMind
• Adaptation: Text-only version (Image processing capabilities removed)

Description

This text-only version of the Gemma 3 model is adapted from Google's original multimodal Gemma 3. By removing the image processing capabilities, it retains the text generation capabilities. With a 128K context window and multilingual support in over 140 languages, it can handle various text generation tasks, such as question answering, summarization, and reasoning. This adaptation makes the model more lightweight and suitable for text-only processing environments or those with resource constraints.

Inputs and outputs

• Input:
  • Text string, such as a question, a prompt, or a document to be summarized.
  • Total input context of 128K tokens for the 27B size.
• Output:
  • Generated text in response to the input, such as an answer to a question or a summary of a document.
  • Total output context of 8192 tokens.

Adaptation Details

This adaptation:

1. Removes the image processing components from the model.
2. Maintains the same text tokenization and generation capabilities.
3. Is compatible with standard text-only inference pipelines.
4. Can be used with regular AutoModelForCausalLM instead of requiring specialized multimodal classes.

📄 License

The license for this model is gemma.

📦 Installation

The provided README does not contain installation steps, so this section is skipped.

🔧 Technical Details

The provided README does not contain detailed technical implementation information, so this section is skipped.