RichardErkhov/OEvortex_-_HelpingAI-Lite-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

HelpingAI-Lite - GGUF

• Model creator: https://huggingface.co/OEvortex/
• Original model: https://huggingface.co/OEvortex/HelpingAI-Lite/

Name	Quant method	Size
HelpingAI-Lite.Q2_K.gguf	Q2_K	0.4GB
HelpingAI-Lite.IQ3_XS.gguf	IQ3_XS	0.44GB
HelpingAI-Lite.IQ3_S.gguf	IQ3_S	0.47GB
HelpingAI-Lite.Q3_K_S.gguf	Q3_K_S	0.47GB
HelpingAI-Lite.IQ3_M.gguf	IQ3_M	0.48GB
HelpingAI-Lite.Q3_K.gguf	Q3_K	0.51GB
HelpingAI-Lite.Q3_K_M.gguf	Q3_K_M	0.51GB
HelpingAI-Lite.Q3_K_L.gguf	Q3_K_L	0.55GB
HelpingAI-Lite.IQ4_XS.gguf	IQ4_XS	0.57GB
HelpingAI-Lite.Q4_0.gguf	Q4_0	0.59GB
HelpingAI-Lite.IQ4_NL.gguf	IQ4_NL	0.6GB
HelpingAI-Lite.Q4_K_S.gguf	Q4_K_S	0.6GB
HelpingAI-Lite.Q4_K.gguf	Q4_K	0.62GB
HelpingAI-Lite.Q4_K_M.gguf	Q4_K_M	0.62GB
HelpingAI-Lite.Q4_1.gguf	Q4_1	0.65GB
HelpingAI-Lite.Q5_0.gguf	Q5_0	0.71GB
HelpingAI-Lite.Q5_K_S.gguf	Q5_K_S	0.71GB
HelpingAI-Lite.Q5_K.gguf	Q5_K	0.73GB
HelpingAI-Lite.Q5_K_M.gguf	Q5_K_M	0.73GB
HelpingAI-Lite.Q5_1.gguf	Q5_1	0.77GB
HelpingAI-Lite.Q6_K.gguf	Q6_K	0.84GB
HelpingAI-Lite.Q8_0.gguf	Q8_0	1.09GB

Original model description:

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! <|user|> Write me a function to search for OEvortex on youtube use Webbrowser . <|assistant|> - text: | <|system|> You are a chatbot who can be a teacher! <|user|> Explain me working of AI . <|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

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"])