Upload README.md

README.md

@@ -5,54 +5,91 @@ license: mit
 
 # model-card-testing
 
-model-card-testing is a pretrained language model that can be used for text generation. Users of this model card should also consider information about the design, traiing, and limitations of gpt2.
+model-card-testing is a pretrained language model that can be used for text generation. Users of this model card should also consider information about the design, training, and limitations of gpt2.
 
 ## Model Details
 
 - **Developed by:** author1, author2
 - **Model type:** testing type
-- **Language(s):** 
-- **License:** 
+- **Language(s):**  # not working right now
+- **License:**  # not working right now
 - **Model Description:** testing description
+- **Related Models:** 
+    - **Parent Model**: gpt2
+    - **Sibling Models**: TO DO (could we do this automatically somehow?)
 
-## Intended Uses & Limitations
+## How to Get Started with the Model 
+
+Use the code below to get started with the model. 
 
-This model can be used for text generation.
 
-#### How to Use
 
-You can get started with the model with code like the following:
 
-```python
-# You can include sample code which will be formatted
-```
 
 Here is how to use this model to get the features of a given text in Pytorch: 
 
+NOTE: This will need customization/fixing.
+
 ```python
-# PyTorch usage
+from transformers import GPT2Tokenizer, GPT2Model
+tokenizer = GPT2Tokenizer.from_pretrained('model-card-testing')
+model = GPT2Model.from_pretrained('model-card-testing')
+text = "Replace me by any text you'd like."
+encoded_input = tokenizer(text, return_tensors='pt')
+output = model(**encoded_input)
 ```
 
 and in TensorFlow: 
 
+NOTE: This will need customization/fixing.
+
 ```python
-# Tensorflow usage
+from transformers import GPT2Tokenizer, TFGPT2Model
+tokenizer = GPT2Tokenizer.from_pretrained('model-card-testing')
+model = TFGPT2Model.from_pretrained('model-card-testing')
+text = "Replace me by any text you'd like."
+encoded_input = tokenizer(text, return_tensors='tf')
+output = model(encoded_input)
 ```
 
-#### Limitations and Bias
+## Intended Uses & Limitations
+LLMs are intended to be used for language generation or as a pretrained base model that can be further fine-tuned for specific tasks. Use cases below are not exhaustive.
+
+#### Direct Use
+This model can be used for:
+- Text generation
+- Exploring characterisitics of language generated by a language model 
+    - Examples: Cloze tests, counterfactuals, generations with reframings
+
+#### Downstream Use
+Tasks that leverage language models, including: 
+- Information Extraction, Question Answering, Summarization
+- Writing assistance: Grammar assistance, autocompletion (for normal prose or code)
+- Creative writing and art: exploring the generation of creative, fictional texts; aiding creation of poetry and other literary art.
+- Entertainment: Creation of games, chat bots, and amusing generations.
+
+### Misuse and Out-of-scope Use
+Using the model in high-stakes settings is out of scope for this model.  The model is not designed for critical decisions nor uses with any material consequences on an individual's livelihood or wellbeing. The model outputs content that appears factual but is not correct.
+
+### Limitations
 
 **CONTENT WARNING: Readers should be aware this section contains content that is disturbing, offensive, and can propogate historical and current stereotypes.**
 
-This model can have biased predictions. For example: 
+Significant research has explored bias and fairness issues with models for language generation (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)). This model also has persistent bias issues, as highlighted in these demonstrative examples below. Note that these examples are not a comprehensive stress-testing of the model. Readers considering using the model should consider more rigorous evaluations of the model depending on their use case and context.
+
+
+
+
+
+NOTE: This code will need customization/fixing.
+
+
+
 
-```python
-# Example of biased predictions
-```
 
 ## Training Data
 
-Describe the data you used to train the model.
-If you initialized it with pre-trained weights, add a link to the pre-trained model card or repository with description of the pre-training data.
+model-card-testing was trained using . See the  data card for additional information. 
 
 ## Training Procedure
 
@@ -70,7 +107,9 @@ You can estimate carbon emissions using the [Machine Learning Impact calculator]
 - **Hours used:** 
 - **Cloud Provider:** 
 - **Compute Region:** 
-- **Carbon Emitted** *(Power consumption x Time x Carbon produced based on location of power grid)*: 
+- **Carbon Emitted** *(Power consumption x Time x Carbon produced based on location of power grid)*:
+
+## Add interpretability section?
 
 ### BibTeX Entry and Citation Info