HelpingAI-Lite-1.5T

🌟 HelpingAI-Lite-1.5T Model Card 🌟

📊 Datasets used:

• cerebras/SlimPajama-627B
• HuggingFaceH4/ultrachat_200k
• bigcode/starcoderdata
• HuggingFaceH4/ultrafeedback_binarized
• OEvortex/vortex-mini
• Open-Orca/OpenOrca

🗣️ Language:

• English (en)

🔒 License:

HelpingAI Simplified Universal License (HSUL)

🧠 Model Overview: HelpingAI-Lite-1.5T is an advanced version of the HelpingAI-Lite model, trained on a vast corpus of 1.5 trillion tokens. This extensive training data enables the model to provide precise and insightful responses, particularly for coding tasks.

🔧 Usage Example:

from transformers import pipeline
from accelerate import Accelerator

# Initialize the accelerator
accelerator = Accelerator()

# Initialize the pipeline
pipe = pipeline("text-generation", model="OEvortex/HelpingAI-Lite-1.5T", device=accelerator.device)

# Define the messages
messages = [
    {
        "role": "system",
        "content": "You are a chatbot who can be a teacher",
    },
    {
        "role": "user",
        "content": "Explain me working of AI.",
    },
]

# Prepare the prompt
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)

# Generate predictions
outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)

# Print the generated text
print(outputs[0]["generated_text"])