README.md

metadata

datasets:
  - cerebras/SlimPajama-627B
  - HuggingFaceH4/ultrachat_200k
  - bigcode/starcoderdata
  - HuggingFaceH4/ultrafeedback_binarized
  - OEvortex/vortex-mini
  - Open-Orca/OpenOrca
language:
  - en
metrics:
  - accuracy
  - speed
library_name: transformers
tags:
  - coder
  - Text-Generation
  - Transformers
  - HelpingAI
license: mit
widget:
  - text: |
      <|system|>
      You are a chatbot who can code!</s>
      <|user|>
      Write me a function to search for OEvortex on youtube use Webbrowser .</s>
      <|assistant|>
  - text: |
      <|system|>
      You are a chatbot who can be a teacher!</s>
      <|user|>
      Explain me working of AI .</s>
      <|assistant|>

HelpingAI-Lite-1T

Subscribe to my YouTube channel

Subscribe

HelpingAI-Lite is a lite version of the HelpingAI model that can assist with coding tasks. It's trained on a diverse range of datasets and fine-tuned to provide accurate and helpful responses.

License

This model is licensed under MIT.

Datasets

The model was trained on the following datasets:

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

Language

The model supports English language.

Usage

CPU and GPU code

from transformers import pipeline
from accelerate import Accelerator

# Initialize the accelerator
accelerator = Accelerator()

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

# Define the messages
messages = [
    {
        "role": "system",
        "content": "You are a chatbot who can help code!",
    },
    {
        "role": "user",
        "content": "Write me a function to calculate the first 10 digits of the fibonacci sequence in Python and print it out to the CLI.",
    },
]

# 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"])