Calme 3.1 Instruct 78b

🚀 MaziyarPanahi/calme-3.1-instruct-78b

This model is an advanced iteration of the powerful Qwen/Qwen2.5-72B, fine - tuned to enhance its capabilities in generic domains. The Qwen2.5-72B base model was self - merged to create a larger model and then fine - tuned on custom datasets.

🚀 Quick Start

Usage Examples

Basic Usage

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

messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe = pipeline("text-generation", model="MaziyarPanahi/calme-3.1-instruct-78b")
pipe(messages)

Advanced Usage

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/calme-3.1-instruct-78b")
model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/calme-3.1-instruct-78b")

✨ Features

• Advanced Iteration: Based on the powerful Qwen/Qwen2.5-72B, it has been further enhanced through self - merging and fine - tuning on custom datasets.
• Generic Domain Capability: Fine - tuned to perform well in a wide range of generic domains.

📦 Installation

This section is skipped as no specific installation steps are provided in the original document.

📚 Documentation

Prompt Template

This model uses the ChatML prompt template:

<|im_start|>system
{System}
<|im_end|>
<|im_start|>user
{User}
<|im_end|>
<|im_start|>assistant
{Assistant}

Evaluation Results

🏆 Open LLM Leaderboard Evaluation Results Detailed results can be found here

Quantized GGUF

Thanks to mradermacher: calme-3.1-instruct-78b-GGUF

🔧 Technical Details

This section is skipped as no specific technical details are provided in the original document.

📄 License

The model uses the qwen license. You can find the license details here.

Additional Information

💡 Usage Tip

This is an experimental model, so it might not perform well for some prompts and may be sensitive to hyperparameters. I would appreciate any feedback to see if I can fix any issues in the next iteration. ❤️

Ethical Considerations

As with any large language model, users should be aware of potential biases and limitations. We recommend implementing appropriate safeguards and human oversight when deploying this model in production environments.