Catppt Base

🚀 😸 CatPPT

"CatPPT" is the ideal alternative to other well - known models. It is created by merging the openchat and neuralchat models using the Gradient SLERP method, resulting in [rishiraj/CatPPT - base](https://huggingface.co/rishiraj/CatPPT - base). Then, it is finetuned on the no_robots dataset for chat.

This is the top - performing 7B model on the leaderboard, completely free from any evaluation data contamination.

🚀 Quick Start

The model is ready to use right after being loaded. You can follow the inference procedure below to start interacting with it.

✨ Features

• High - Performance: It ranks at the top among 7B models on the leaderboard.
• Contamination - Free: Free from any evaluation data contamination.
• Created through Merging: Developed by merging openchat and neuralchat models using the Gradient SLERP method and then finetuned for chat.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

Here's how you can run the model using the pipeline() function from 🤗 Transformers:

import torch
from transformers import pipeline

pipe = pipeline("text - generation", model="rishiraj/CatPPT", torch_dtype=torch.bfloat16, device_map="auto")

# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
messages = [
    {
        "role": "system",
        "content": "You are a friendly chatbot who always responds in the style of a pirate"
    },
    {
        "role": "user",
        "content": "How many helicopters can a human eat in one sitting?"
    }
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

📚 Documentation

Model date

rishiraj/CatPPT was trained between 15th and 17th December, 2023.

Evaluation

It achieves the following results on the Open_LLM_Leaderboard. At the time of release, CatPPT is the highest - ranked 7B chat model on the leaderboard, that's free from evaluation data contamination.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e - 05
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• distributed_type: multi - GPU
• gradient_accumulation_steps: 128
• total_train_batch_size: 512
• optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
• lr_scheduler_type: cosine
• num_epochs: 1

Training results

Framework versions

• Transformers 4.36.1
• Pytorch 2.1.2+cu121
• Datasets 2.14.6
• Tokenizers 0.15.0
• PEFT 0.6.1

Citation Information

@misc{rishiraj2023catppt,
  author = {Rishiraj Acharya},
  title = {CatPPT},
  year = {2023},
  publisher = {Hugging Face},
  journal = {Hugging Face repository},
  howpublished = {\url{https://huggingface.co/rishiraj/CatPPT}}
}

📄 License

This project is licensed under the Apache 2.0 license.