Aira-OPT-125M
Aira-2 is the second version of the Aira instruction-tuned series. Aira-OPT-125M is an instruction-tuned OPT-style model based on OPT. The model was trained with a dataset composed of prompts and completions generated synthetically by prompting already-tuned models (ChatGPT, Llama, Open-Assistant, etc).
Check our gradio-demo in Spaces.
Details
- Size: 125,237,760 parameters
- Dataset: Instruct-Aira Dataset
- Language: English
- Number of Epochs: 5
- Batch size: 32
- Optimizer:
torch.optim.AdamW(warmup_steps = 1e2, learning_rate = 5e-4, epsilon = 1e-8) - GPU: 1 NVIDIA A100-SXM4-40GB
- Emissions: 0.25 KgCO2 (Singapore)
- Total Energy Consumption: 0.52 kWh
This repository has the notebook used to train this model.
Usage
Three special tokens are used to mark the user side of the interaction and the model's response:
<|startofinstruction|>What is a language model?<|endofinstruction|>A language model is a probability distribution over a vocabulary.<|endofcompletion|>
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
tokenizer = AutoTokenizer.from_pretrained('nicholasKluge/Aira-OPT-125M')
aira = AutoModelForCausalLM.from_pretrained('nicholasKluge/Aira-OPT-125M')
aira.eval()
aira.to(device)
question = input("Enter your question: ")
# OPT tokenizer already adds the BOS token, so we do not need to add it manually
inputs = tokenizer(question + tokenizer.sep_token, return_tensors="pt").to(device)
responses = aira.generate(**inputs,
bos_token_id=tokenizer.bos_token_id,
pad_token_id=tokenizer.pad_token_id,
eos_token_id=tokenizer.eos_token_id,
do_sample=True,
top_k=50,
max_length=500,
top_p=0.95,
temperature=0.7,
num_return_sequences=2)
print(f"Question: 👤 {question}\n")
for i, response in enumerate(responses):
print(f'Response {i+1}: 🤖 {tokenizer.decode(response, skip_special_tokens=True).replace(question, "")}')
The model will output something like:
>>>Question: 👤 What is the capital of Brazil?
>>>Response 1: 🤖 The capital of Brazil is BrasÃlia.
>>>Response 2: 🤖 The capital of Brazil is BrasÃlia.
Limitations
🤥 Generative models can perpetuate the generation of pseudo-informative content, that is, false information that may appear truthful.
🤬 In certain types of tasks, generative models can produce harmful and discriminatory content inspired by historical stereotypes.
Evaluation
| Model (OPT) | Average | ARC | TruthfulQA | ToxiGen | ||
|---|---|---|---|---|---|---|
| Aira-OPT-125M | 43.34 | 24.65 | 49.11 | 56.27 | ||
| OPT-125M | 40.29 | 22.78 | 42.88 | 55.21 | ||
| Aira-OPT-350M | 41.56 | 25.00 | 42.13 | 57.55 | ||
| OPT-350M | 40.62 | 23.97 | 41.00 | 56.91 | ||
| Aira-OPT-1B3 | 43.90 | 28.41 | 46.59 | 56.70 | ||
| OPT-1.3b | 40.91 | 29.69 | 38.68 | 54.36 |
- Evaluations were performed using the Language Model Evaluation Harness (by EleutherAI). The notebook used to make these evaluations is available in the this repo.
Cite as 🤗
@misc{nicholas22aira,
doi = {10.5281/zenodo.6989727},
url = {https://huggingface.co/nicholasKluge/Aira-OPT-125M},
author = {Nicholas Kluge Corrêa},
title = {Aira},
year = {2023},
publisher = {HuggingFace},
journal = {HuggingFace repository},
}
License
The Aira-OPT-125M is licensed under the OPT-175B License Agreement, Copyright (c) Meta Platforms, Inc. All Rights Reserved. See the LICENSE file for more details.
