DeciLM-6b

DeciLM 6B

DeciLM 6B is a 5.7 billion parameter decoder-only text generation model. With a context window of 4096 tokens, the highly efficient model uses variable Grouped-Query Attention (GQA) to achieve an optimal balance between performance and computational efficiency. The model's architecture was generated using Deci's proprietary Neural Architecture Search-based technology, AutoNAC.

Model Details

Model Description

Deci developed and publically released the DeciLM 6B large language model, a pretrained, high-efficiency generative text model with 5.7 billion parameters. DeciLM 6B outpaces pretrained models in its class, with a throughput that's up to 15 times that of Llama 2 7B's. DeciLM-6B was further fine-tuned using LoRA for instruction following on a subset of the OpenOrca dataset, creating DeciLM 6B-Instruct

• Developed by: Deci
• Model type: DeciLM is an auto-regressive language model using an optimized transformer decoder architecture that includes variable Grouped-Query Attention.
• Language(s) (NLP): English
• License: Llama 2 Community License Agreement with an extention of Deci regarding hosting service providers.

Model Architecture

*AutoNAC was employed to optimize the selection of the GQA num_key_value_heads for each layer of the model.

• Decoder layer: Varible Grouped Query Attention. Grouped Query Attention (GQA) was introduced in Ainslie et al., 2023
• Position Embeddings: Dynamic NTK Scaling Rotary Position Embeddings Su et al., 2021

Model Sources

• Paper: DeciLM Technical Blog
• Demo: DeciLM 6B Instruct Demo
• Notebook: DeciLM 6B Notebook

Uses

The model is intended for commercial and research use in English and can be fine-tuned for use in other languages.

How to Get Started with the Model

Use the code below to get started with the model.

# pip install -q transformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

checkpoint = "Deci/DeciLM-6b"
device = "cuda" # for GPU usage or "cpu" for CPU usage

tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForCausalLM.from_pretrained(checkpoint, torch_dtype=torch.bfloat16, trust_remote_code=True).to(device)

inputs = tokenizer.encode("In a shocking finding, scientists discovered a herd of unicorns living in", return_tensors="pt").to(device)
outputs = model.generate(inputs, max_new_tokens=100, do_sample=True, top_p=0.95)
print(tokenizer.decode(outputs[0]))

Training Details

DeciLM 6B underwent training utilizing a subset of the SlimPajamas dataset, leveraging advanced proprietary methodologies allowing for fast training.

Evaluation

Below are DeciLM's 6B evaluation results.

Runtime Benchmarks

• Throughput (tokens/sec) - Measured with optimal batch - PyTorch BS 64, Infery LLM BS 128
• In order to replicate the results of the PyTorch benchmark, use this code example

How to Cite

Please cite this model using this format.

@misc{DeciFoundationModels,
title = {DeciLM 6B},
author = {DeciAI Research Team},
year = {2023}
url={[https://huggingface.co/Deci/DeciLM-6b](https://huggingface.co/Deci/DeciLM-6b)},
}