Deci/DeciLM-6b-instruct

DeciLM 6B-Instruct

DeciLM 6B-Instruct is a model for short-form instruction following. It is built by LoRA fine-tuning DeciLM 6B on a subset of the OpenOrca dataset.

• 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 Sources

• Paper: DeciLM 6B Technical Blog
• Demo: DeciLM 6B-Instruct Demo
• Notebook: DeciLM 6B-Instruct 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-instruct"
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("How do I make french toast? Think through it step by step", 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 the SlimPijamas dataset, leveraging advanced proprietary methodologies allowing for fast training. DeciLM 6B was further finetuned on a subset of the OpenOrca dataset, giving rise to DeciLM-6B-Instruct.

Evaluation

Below are DeciLM's 6B-instruct evaluation results.

Average	ARC Challenge*	ARC Easy*	BoolQ	HellaSwag*	LAMBDA OpenAI	OpenBookQA	PIQA	TruthfulQA	Winogrande
62.01	44.43	70.58	77.34	74.57	70.1	33	77.52	43.89	67.64
Accuracy-norm score*

Runtime Benchmarks

Inference Tool/Hardware	A10 (tokens/sec)
PyTorch	652.49
Infery LLM	2,029.6

• 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

Disclaimer

DeciLM 6B-Instruct has not been aligned for safety or trained using RLHF.

How to Cite

Please cite this model using this format.

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