Minitron 8B Base

🚀 Minitron-8B-Base

Minitron-8B-Base is a large language model derived from pruning Nemotron-4 15B, offering significant computational savings and comparable performance to other community models.

🚀 Quick Start

Support for this model will be added in the upcoming transformers release. In the meantime, you can install the library from source:

pip install git+https://github.com/huggingface/transformers

The following is an example of how to load the Minitron-8B model and use it for text generation:

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
model_path = "nvidia/Minitron-8B-Base"
tokenizer = AutoTokenizer.from_pretrained(model_path)

device='cuda'
dtype=torch.bfloat16
model = AutoModelForCausalLM.from_pretrained(model_path, torch_dtype=dtype, device_map=device)

# Prepare the input text
prompt = "To be or not to be,"
input_ids = tokenizer.encode(prompt, return_tensors="pt").to(model.device)

# Generate the output
output_ids = model.generate(input_ids, max_length=50, num_return_sequences=1)

# Decode and print the output
output_text = tokenizer.decode(output_ids[0], skip_special_tokens=True)
print(output_text)

✨ Features

• Efficient Training: Deriving the Minitron 8B and 4B models from the base 15B model using our approach requires up to 40x fewer training tokens per model compared to training from scratch, resulting in compute cost savings of 1.8x for training the full model family (15B, 8B, and 4B).
• Good Performance: Minitron models exhibit up to a 16% improvement in MMLU scores compared to training from scratch, perform comparably to other community models such as Mistral 7B, Gemma 7B and Llama-3 8B, and outperform state-of-the-art compression techniques from the literature.

📦 Installation

Support for this model will be added in the upcoming transformers release. In the meantime, please install the library from source:

pip install git+https://github.com/huggingface/transformers

💻 Usage Examples

Basic Usage

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
model_path = "nvidia/Minitron-8B-Base"
tokenizer = AutoTokenizer.from_pretrained(model_path)

device='cuda'
dtype=torch.bfloat16
model = AutoModelForCausalLM.from_pretrained(model_path, torch_dtype=dtype, device_map=device)

# Prepare the input text
prompt = "To be or not to be,"
input_ids = tokenizer.encode(prompt, return_tensors="pt").to(model.device)

# Generate the output
output_ids = model.generate(input_ids, max_length=50, num_return_sequences=1)

# Decode and print the output
output_text = tokenizer.decode(output_ids[0], skip_special_tokens=True)
print(output_text)

📚 Documentation

Model Overview

Minitron-8B-Base is a large language model (LLM) obtained by pruning Nemotron-4 15B. Specifically, we prune model embedding size, number of attention heads, and MLP intermediate dimension. After pruning, we perform continued training with distillation using 94 billion tokens to get the final model. We use the continuous pre-training data corpus used in Nemotron-4 15B for this.

This model is for research and development only.

Model Developer: NVIDIA

Model Dates: Minitron-8B-Base was trained between February 2024 and June 2024.

Model Architecture

Dataset & Training

Evaluation Results

5-shot performance. Language Understanding evaluated using Massive Multitask Language Understanding:

Zero-shot performance. Evaluated using select datasets from the LM Evaluation Harness with additions:

Code generation performance. Evaluated using HumanEval:

Please refer to our paper for the full set of results.

Inference

Limitations

The model was trained on data that contains toxic language, unsafe content, and societal biases originally crawled from the internet. Therefore, the model may amplify those biases and return toxic responses especially when prompted with toxic prompts. The model may generate answers that may be inaccurate, omit key information, or include irrelevant or redundant text producing socially unacceptable or undesirable text, even if the prompt itself does not include anything explicitly offensive.

Ethical Considerations

NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. Please report security vulnerabilities or NVIDIA AI Concerns here.

Citation

If you find our work helpful, please consider citing our paper:

@article{minitron2024,
      title={Compact Language Models via Pruning and Knowledge Distillation}, 
      author={Saurav Muralidharan and Sharath Turuvekere Sreenivas and Raviraj Joshi and Marcin Chochowski and Mostofa Patwary and Mohammad Shoeybi and Bryan Catanzaro and Jan Kautz and Pavlo Molchanov},
      journal={arXiv preprint arXiv:2407.14679},
      year={2024},
      url={https://arxiv.org/abs/2407.14679}, 
}

📄 License

Minitron-8B-Base is released under the NVIDIA Open Model License Agreement.