🚀 LaMini-GPT-774M
LaMini-GPT-774M is a fine - tuned language model in the LaMini - LM series. It is based on the gpt2 - large model and fine - tuned on a large - scale instruction dataset, aiming to effectively respond to natural - language instructions.
🚀 Quick Start
Intended use
We recommend using the model to respond to human instructions written in natural language. Since this decoder - only model is fine - tuned with wrapper text, we suggest using the same wrapper text to achieve the best performance. See the example on the right or the code below.
We now show you how to load and use our model using HuggingFace pipeline()
.
from transformers import pipeline
checkpoint = "{model_name}"
model = pipeline('text-generation', model = checkpoint)
instruction = 'Please let me know your thoughts on the given place and why you think it deserves to be visited: \n"Barcelona, Spain"'
input_prompt = f"Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response:"
generated_text = model(input_prompt, max_length=512, do_sample=True)[0]['generated_text']
print("Response", generated_text)
✨ Features
- Instruction - following: Capable of responding to natural - language instructions.
- Fine - tuned: Based on gpt2 - large and fine - tuned on a large - scale instruction dataset.
📦 Installation
The code example above shows that you need to install the transformers
library:
pip install -q transformers
📚 Documentation
Model Introduction
This model is one of our LaMini - LM model series in paper "[LaMini - LM: A Diverse Herd of Distilled Models from Large - Scale Instructions](https://github.com/mbzuai - nlp/lamini - lm)". This model is a fine - tuned version of [gpt2 - large](https://huggingface.co/gpt2 - large) on [LaMini - instruction dataset](https://huggingface.co/datasets/MBZUAI/LaMini - instruction) that contains 2.58M samples for instruction fine - tuning. For more information about our dataset, please refer to our [project repository](https://github.com/mbzuai - nlp/lamini - lm/).
You can view other models of LaMini - LM series as follows. Models with ✩ are those with the best overall performance given their size/architecture, hence we recommend using them. More details can be seen in our paper.
Training Procedure
We initialize with [gpt2 - large](https://huggingface.co/gpt2 - large) and fine - tune it on our [LaMini - instruction dataset](https://huggingface.co/datasets/MBZUAI/LaMini - instruction). Its total number of parameters is 774M.
Training Hyperparameters
[No specific hyperparameters provided in the original text]
Evaluation
We conducted two sets of evaluations: automatic evaluation on downstream NLP tasks and human evaluation on user - oriented instructions. For more detail, please refer to our paper.
Limitations
More information needed
🔧 Technical Details
The model is initialized with [gpt2 - large](https://huggingface.co/gpt2 - large) and fine - tuned on the [LaMini - instruction dataset](https://huggingface.co/datasets/MBZUAI/LaMini - instruction). Its total number of parameters is 774M.
📄 License
This model is licensed under [CC By NC 4.0](https://creativecommons.org/licenses/by - nc/4.0/).
Citation
@article{lamini - lm,
author = {Minghao Wu and
Abdul Waheed and
Chiyu Zhang and
Muhammad Abdul - Mageed and
Alham Fikri Aji
},
title = {LaMini - LM: A Diverse Herd of Distilled Models from Large - Scale Instructions},
journal = {CoRR},
volume = {abs/2304.14402},
year = {2023},
url = {https://arxiv.org/abs/2304.14402},
eprinttype = {arXiv},
eprint = {2304.14402}
}