Deci AI DeciLM Instruction

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.

Model Sources

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

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)},
}