EZO Llama 3.2 3B Instruct Dpoe

🚀 AXCXEPT/EZO-Llama-3.2-3B-Instruct-dpoE

This model is based on Meta AI's Llama 3.2, fine - tuned to enhance performance on Japanese tasks.

📚 Documentation

Model Information

This model is based on Meta AI's Llama 3.2 with fine tuning to improve performance on Japanese tasks. Based on the base Llama-3.2-3B-Instruct, performance was improved on the Japanese-English dataset.

Legal Notice

This model is subject to the Llama 3.2 Community License Agreement. For detailed information, please refer to the official Llama license page: Llama 3.2 License

💻 Usage Examples

Basic Usage

import torch
from transformers import pipeline

model_id = "AXCXEPT/EZO-Llama-3.2-3B-Instruct-dpoE"
pipe = pipeline(
    "text-generation",
    model=model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
messages = [
    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
    {"role": "user", "content": "Who are you?"},
]
outputs = pipe(
    messages,
    max_new_tokens=256,
)
print(outputs[0]["generated_text"][-1])

📊 Benchmark Results

Disclaimer

This model is provided for research and development purposes only and should be considered an experimental prototype. It is not intended for commercial use or deployment in mission - critical environments. Use of this model is at the user's own risk and its performance and results are not guaranteed. Axcxept Corporation shall not be liable for any direct, indirect, special, incidental, or consequential damages or any loss whatsoever resulting from the use of this model, regardless of the results obtained. Users fully understand the risks associated with the use of this model and use it at their own discretion.

Hardware

H100 × 8(Running in 3h)

👏 Credits

This model is based on Meta AI's Llama 3.2. We acknowledge and thank the Meta AI team for their work on the base model.

📄 License

This model is under the llama3.2 license.