README.md

metadata

datasets:
  - cerebras/SlimPajama-627B
  - HuggingFaceH4/ultrachat_200k
  - bigcode/starcoderdata
  - HuggingFaceH4/ultrafeedback_binarized
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|>
model-index:
  - name: HelpingAI-Lite
    results:
      - task:
          type: text-generation
        metrics:
          - name: Epoch
            type: Training Epoch
            value: 3
          - name: Eval Logits/Chosen
            type: Evaluation Logits for Chosen Samples
            value: -2.707406759262085
          - name: Eval Logits/Rejected
            type: Evaluation Logits for Rejected Samples
            value: -2.65652441978546
          - name: Eval Logps/Chosen
            type: Evaluation Log-probabilities for Chosen Samples
            value: -370.129670421875
          - name: Eval Logps/Rejected
            type: Evaluation Log-probabilities for Rejected Samples
            value: -296.073825390625
          - name: Eval Loss
            type: Evaluation Loss
            value: 0.513750433921814
          - name: Eval Rewards/Accuracies
            type: Evaluation Rewards and Accuracies
            value: 0.738095223903656
          - name: Eval Rewards/Chosen
            type: Evaluation Rewards for Chosen Samples
            value: -0.0274422804903984
          - name: Eval Rewards/Margins
            type: Evaluation Rewards Margins
            value: 1.008722543614307
          - name: Eval Rewards/Rejected
            type: Evaluation Rewards for Rejected Samples
            value: -1.03616464138031
          - name: Eval Runtime
            type: Evaluation Runtime
            value: 93.5908
          - name: Eval Samples
            type: Number of Evaluation Samples
            value: 2000
          - name: Eval Samples per Second
            type: Evaluation Samples per Second
            value: 21.37
          - name: Eval Steps per Second
            type: Evaluation Steps per Second
            value: 0.673

QuantFactory/HelpingAI-Lite-GGUF

This is quantized version of OEvortex/HelpingAI-Lite created using llama.cpp

Original Model Card

HelpingAI-Lite

Subscribe to my YouTube channel

Subscribe

GGUF version here

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

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"])