language:
- en
datasets:
- English
tags:
- text generation
- pytorch
- causal-lm
- Writer-data
pipeline_tag: text-generation
library_name: transformers
license: cc-by-4.0
Palmyra-small
|
Model Description
Palmyra was primarily pretrained with English text, there is still a trace amount of non-English data present within the training corpus that was accessed through CommonCrawl. A causal language modeling (CLM) objective was utilized during the process of the model's pretraining. Similar to GPT-3, Palmyra is a member of the same family of models that only contain a decoder. As a result, it was pretrained utilizing the objective of self-supervised causal language modeling. Palmyra uses the prompts and general experimental setup from GPT-3 in order to conduct its evaluation in accordance with GPT-3. Read the official paper if you want more information about this.
Training data
Palmyra-small 128M was trained on Writer custom dataset
Intended Use and Limitations
Palmyra-small learns an inner representation of the English language that can be used to extract features useful for downstream tasks. The model is best at what it was pretrained for however, which is generating text from a prompt.
How to use
This model can be easily loaded using the AutoModelForCausalLM functionality:
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model = AutoModelForCausalLM.from_pretrained("Writer/palmyra-small", torch_dtype=torch.float16).cuda()
# the fast tokenizer currently does not work correctly
tokenizer = AutoTokenizer.from_pretrained("Writer/palmyra-small", use_fast=False)
prompt = "What is the color of a carrot?\nA:"
input_ids = tokenizer(prompt, return_tensors="pt").input_ids.cuda()
generated_ids = model.generate(input_ids)
tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
Limitations and Biases
Palmyra's core functionality is to take a string of text and predict the next token. While language models are widely used for other tasks, there are many unknowns in this work. When prompting Palmyra, keep in mind that the statistically most likely next token is not always the token that produces the most "accurate" text. Never rely on Palmyra to produce factually correct results.
Palmyra was trained on Writer custom data. As with all language models, it is difficult to predict how Palmyra will respond to specific prompts, and offensive content may appear unexpectedly. We recommend that the outputs be curated or filtered by humans before they are released, both to censor undesirable content and to improve the quality of the results.
Evaluation results
Evaluation of Palmyra-small model on the SuperGLUE benchmark |------------|--------|-------|
| Task | Metric | Value |
|---|---|---|
| boolq | acc | 64.43 |
| cb | acc | 10.71 |
| f1 | 08.32 | |
| copa | acc | 76.00 |
| multirc | acc | 01.26 |
| record | f1 | 84.02 |
| em | 83.29 | |
| wic | acc | 50.00 |
| wsc | acc | 36.54 |
Citation and Related Information
To cite this model:
@misc{Palmyra,
author = {Kiran and Komatsuzaki, Aran},
title = {{GPT-J-6B: A 6 Billion Parameter Autoregressive Language Model}},
howpublished = {\url{https://github.com/kingoflolz/mesh-transformer-jax}},
year = 2021,
month = May
}