Team Ai
Modelpublic

OEvortex/HelpingAI-Lite-1.5T

sourceHugging Faceotherupdated 3y agoView on Hugging Face
2likes69downloads
Model Card

🌟 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:

python
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"])