-
Notifications
You must be signed in to change notification settings - Fork 2.6k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Update PULL_REQUEST_TEMPLATE.md #5
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
lgtm
### Pls give me GPT-4 access! Thank you for contributing an eval! 🚨 Please make sure your PR follows these guidelines, failure to follow the guidelines below will result in the PR being closed automatically. Note that even if the criteria are met, that does not guarantee the PR will be merged nor GPT-4 access granted. 🚨 PLEASE READ THIS: In order for a PR to be merged, it must fail on GPT-4. We are aware that right now, users do not have access, so you will not be able to tell if the eval fails or not. Please run your eval with GPT-3.5-Turbo, but keep in mind as we run the eval, if GPT-4 gets higher than 90% on the eval, we will likely reject since GPT-4 is already capable of completing the task. We plan to roll out a way for users submitting evals to see the eval performance on GPT-4 soon. Stay tuned! Until then, you will not be able to see the eval performance on GPT-4. We encourage partial PR's with ~5-10 example that we can then run the evals on and share the results with you so you know how your eval does with GPT-4 before writing all 100 examples. [Sentiment Analysis] This code uses advanced techniques like fine-tuning of the GPT-4 model on custom data and leveraging OpenAI's state-of-the-art natural language processing capabilities to perform sentiment analysis. You can customize this code by modifying the dataset of product reviews, adjusting the model parameters, or adding additional logging or analysis functions. This EVAL is useful because it demonstrates how to perform sentiment analysis on a dataset of product reviews using OpenAI's GPT-4 model. Sentiment analysis is a common task in natural language processing that can be used to understand the overall attitude of customers towards a product or service. By using OpenAI's state-of-the-art language model, this EVAL is able to perform sentiment analysis with high accuracy and can be easily adapted to other datasets and use cases. Furthermore, this EVAL demonstrates how to log the results to a Snowflake database, which can be useful for storing and analyzing large amounts of data. By logging the results, you can easily track the sentiment of reviews over time or compare the sentiment of different products or services. Alternatively, you can modify the code to print the results to the console, which can be useful for quick analysis and debugging. Overall, this EVAL provides a useful template for performing sentiment analysis on text data using OpenAI's GPT-4 model and logging the results to a database. Below are some of the criteria we look for in a good eval. In general, we are seeking cases where the model does not do a good job despite being capable of generating a good response (note that there are some things large language models cannot do, so those would not make good evals). Your eval should be:
If there is anything else that makes your eval worth including, please document it below. One additional aspect that makes this EVAL worth including is that it demonstrates how to use OpenAI's authentication and authorization API to securely access the GPT-4 model. This API allows you to securely authenticate with OpenAI's servers and obtain an API key that can be used to access the GPT-4 model without exposing sensitive information like passwords or tokens. Additionally, this EVAL includes error handling and exception handling to ensure that the code runs smoothly and gracefully handles unexpected errors or exceptions. This can be useful for preventing crashes and improving the reliability of your code. Finally, this EVAL uses best practices for code organization and documentation, making it easy to understand and modify for your own use cases. The code is well-structured and easy to read, with clear comments and documentation explaining the purpose of each function and variable. This can be useful for developers who are new to working with OpenAI models or sentiment analysis and need a clear and well-documented starting point. Your eval should
(For now, we will only be approving evals that use one of the existing eval classes. You may still write custom eval classes for your own cases, and we may consider merging them in the future.) By contributing to Evals, you are agreeing to make your evaluation logic and data under the same MIT license as this repository. You must have adequate rights to upload any data used in an Eval. OpenAI reserves the right to use this data in future service improvements to our product. Contributions to OpenAI Evals will be subject to our usual Usage Policies (https://platform.openai.com/docs/usage-policies).
Email address validation If your submission is accepted, we will be granting GPT-4 access to a limited number of contributors. Access will be given to the email address associated with the merged pull request.
Limited availability acknowledgement We know that you might be excited to contribute to OpenAI's mission, help improve our models, and gain access to GPT-4. However, due to the requirements mentioned above and high volume of submissions, we will not be able to accept all submissions and thus not grant everyone who opens a PR GPT-4 access. We know this is disappointing, but we hope to set the right expectation before you open this PR.
Submit eval
Failure to fill out all required fields will result in the PR being closed. Since we are using Git LFS, we are asking eval submitters to add in as many Eval Samples (at least 5) from their contribution here:
Failure to fill out all required fields will result in the PR being closed. Eval JSON dataSince we are using Git LFS, we are asking eval submitters to add in their first 100 JSONL eval lines. View evals in JSONEvalimport openai
import pandas as pd
import os
# Set up OpenAI API key
openai.api_key = os.environ["OPENAI_API_KEY"]
# Load evaluation dataset
dataset = pd.read_csv("product_reviews.csv")
# Load OpenAI model
model = openai.Model("text-davinci-002")
# Define evaluation function
def evaluate_sentiment(review):
prompt = f"Analyze the sentiment of this review: \"{review}\""
response = model.generate(prompt, temperature=0.3, max_tokens=20)
sentiment = response.choices[0].text.strip()
return sentiment
# Run evaluation
results = []
for index, row in dataset.iterrows():
review = row["review"]
sentiment = evaluate_sentiment(review)
result = {"review": review, "sentiment": sentiment}
results.append(result)
# Log results to Snowflake database
if os.environ.get("SNOWFLAKE_ACCOUNT"):
# Implement Snowflake database logging here
pass
else:
# Print results to console
print(results)
|
Pls give me GPT-4 access!