Quantization made by Richard Erkhov.

Aira-2-774M - GGUF

Model creator: https://huggingface.co/nicholasKluge/
Original model: https://huggingface.co/nicholasKluge/Aira-2-774M/

Name	Quant method	Size
Aira-2-774M.Q2_K.gguf	Q2_K	0.32GB
Aira-2-774M.IQ3_XS.gguf	IQ3_XS	0.36GB
Aira-2-774M.IQ3_S.gguf	IQ3_S	0.37GB
Aira-2-774M.Q3_K_S.gguf	Q3_K_S	0.37GB
Aira-2-774M.IQ3_M.gguf	IQ3_M	0.4GB
Aira-2-774M.Q3_K.gguf	Q3_K	0.43GB
Aira-2-774M.Q3_K_M.gguf	Q3_K_M	0.43GB
Aira-2-774M.Q3_K_L.gguf	Q3_K_L	0.46GB
Aira-2-774M.IQ4_XS.gguf	IQ4_XS	0.44GB
Aira-2-774M.Q4_0.gguf	Q4_0	0.46GB
Aira-2-774M.IQ4_NL.gguf	IQ4_NL	0.47GB
Aira-2-774M.Q4_K_S.gguf	Q4_K_S	0.47GB
Aira-2-774M.Q4_K.gguf	Q4_K	0.51GB
Aira-2-774M.Q4_K_M.gguf	Q4_K_M	0.51GB
Aira-2-774M.Q4_1.gguf	Q4_1	0.51GB
Aira-2-774M.Q5_0.gguf	Q5_0	0.55GB
Aira-2-774M.Q5_K_S.gguf	Q5_K_S	0.55GB
Aira-2-774M.Q5_K.gguf	Q5_K	0.59GB
Aira-2-774M.Q5_K_M.gguf	Q5_K_M	0.59GB
Aira-2-774M.Q5_1.gguf	Q5_1	0.6GB
Aira-2-774M.Q6_K.gguf	Q6_K	0.65GB
Aira-2-774M.Q8_0.gguf	Q8_0	0.84GB

Original model description:

license: apache-2.0 datasets: - nicholasKluge/instruct-aira-dataset language: - en metrics: - accuracy library_name: transformers tags: - alignment - instruction tuned - text generation - conversation - assistant pipeline_tag: text-generation widget: - text: "<|startofinstruction|>Can you explain what is Machine Learning?<|endofinstruction|>" example_title: Machine Learning - text: "<|startofinstruction|>Do you know anything about virtue ethics?<|endofinstruction|>" example_title: Ethics - text: "<|startofinstruction|>How can I make my girlfriend happy?<|endofinstruction|>" example_title: Advise inference: parameters: repetition_penalty: 1.2 temperature: 0.2 top_k: 30 top_p: 0.3 max_new_tokens: 200 length_penalty: 0.3 early_stopping: true co2_eq_emissions: emissions: 770 source: CodeCarbon training_type: fine-tuning geographical_location: United States of America hardware_used: NVIDIA A100-SXM4-40GB

Aira-2-774M

Aira-2 is the second version of the Aira instruction-tuned series. Aira-2-774M is an instruction-tuned model based on GPT-2. 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: 774,032,640 parameters
Dataset: Instruct-Aira Dataset
Language: English
Number of Epochs: 3
Batch size: 8
Optimizer: torch.optim.AdamW (warmup_steps = 1e2, learning_rate = 5e-4, epsilon = 1e-8)
GPU: 1 NVIDIA A100-SXM4-40GB
Emissions: 0.77 KgCO2 (Singapore)
Total Energy Consumption: 1.58 kWh

This repository has the source code used to train this model.

Usage

Three special tokens are used to mark the user side of the interaction and the model's response:

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

tokenizer = AutoTokenizer.from_pretrained('nicholasKluge/Aira-2-774M')
aira = AutoModelForCausalLM.from_pretrained('nicholasKluge/Aira-2-774M')

aira.eval()
aira.to(device)

question =  input("Enter your question: ")

inputs = tokenizer(tokenizer.bos_token + question + tokenizer.sep_token,
  add_special_tokens=False,
  return_tensors="pt").to(device)

responses = aira.generate(**inputs,	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 Brasília.
>>>Response 2: 🤖 The capital of Brazil is Brasília.

Limitations

Hallucinations: This model can produce content that can be mistaken for truth but is, in fact, misleading or entirely false, i.e., hallucination.
Biases and Toxicity: This model inherits the social and historical stereotypes from the data used to train it. Given these biases, the model can produce toxic content, i.e., harmful, offensive, or detrimental to individuals, groups, or communities.
Repetition and Verbosity: The model may get stuck on repetition loops (especially if the repetition penalty during generations is set to a meager value) or produce verbose responses unrelated to the prompt it was given.

Evaluation

Model	Average	ARC	TruthfulQA	ToxiGen
Aira-2-124M-DPO	40.68	24.66	42.61	54.79
Aira-2-124M	38.07	24.57	41.02	48.62
GPT-2	35.37	21.84	40.67	43.62
Aira-2-355M	39.68	27.56	38.53	53.19
GPT-2-medium	36.43	27.05	40.76	41.49
Aira-2-774M	42.26	28.75	41.33	56.70
GPT-2-large	35.16	25.94	38.71	40.85
Aira-2-1B5	42.22	28.92	41.16	56.60
GPT-2-xl	36.84	30.29	38.54	41.70

Evaluations were performed using the Language Model Evaluation Harness (by EleutherAI).

Cite as 🤗

@misc{nicholas22aira,
  doi = {10.5281/zenodo.6989727},
  url = {https://github.com/Nkluge-correa/Aira},
  author = {Nicholas Kluge Corrêa},
  title = {Aira},
  year = {2023},
  publisher = {GitHub},
  journal = {GitHub repository},
}

@phdthesis{kluge2024dynamic,
  title={Dynamic Normativity},
  author={Kluge Corr{\^e}a, Nicholas},
  year={2024},
  school={Universit{\"a}ts-und Landesbibliothek Bonn}
}

License

Aira-2-774M is licensed under the Apache License, Version 2.0. See the LICENSE file for more details.