Stack Overflow
Stack Overflow

Questions tagged [gpt-3]

Use this tag with Generative Pre-trained Transformer 3 (GPT-3). Do not use with GPT-2 or the ad tagging library (GPT).

References:

GPT-3 (Wikipedia)

Related tags:

296 questions
0
votes
1 answer

OpenAI GPT-3 API error: "InvalidRequestError: Unrecognized request argument supplied"

import openai # Set the API key openai.api_key = "YOUR API KEY" # Define the conversation memory conversation_memory = { "previous_question": "What is the capital of France?", "previous_answer": "The capital of France is Paris." } # Make…
Richard Twitty
  • 120
  • 2
  • 8
0
votes
0 answers

torch parameter is going to nan when after first optim.step() while doing GPT's downstream task

Foundation I'm doing finetuning with GPTJForCausalLM. (pretrained is 6B and fp16). Environment ubuntu 20.04 (nvidia-docker) cuda(in docker) version is 11.4 RTX 3090 (24G VRAM) torch.__version__ 1.12.1 transformers.__version__ 4.12.5 jupyter lab…
user1101221
  • 394
  • 6
  • 21
0
votes
1 answer

Is it possible to use continue in the Open AI API?

I am testing using the Open AI API with the end-point: https://api.openai.com/v1/completions But, I find that on the website https://chat.openai.com/chat , we can simplely use the continue to ask the AI to give the answer with the context. And we…
qus
  • 9
  • 3
0
votes
0 answers

How to return an image as a response in Django

Doing a POST request to GPT-3 in order to get code completion output when I send some input. I seem to be getting the response I expect, but cannot actually get the code written by GPT-3. This is the response I get: ".\n\n## Challenge\n\nWrite a…
Emm
  • 2,367
  • 3
  • 24
  • 50
0
votes
0 answers

embeddings distribution wrong

I'm having the code below which is supposed to plot word embeddings. Since it creates a list of embeddings of identical words I would have expected a cluster of points - all embeddings at one point. But they are scattered like this. Any Idea what I…
HeikoG
  • 1,793
  • 1
  • 20
  • 29
0
votes
1 answer

GPT3 conversational Discord bot stops working after 5-6 sentences

I am creating a fun Discord bot which talks like my imaginary crush, lol! The problem is that its working for the first 5-6 lines but then gives this error import openai openai.api_key = "Hidden" DISCORD_BOT_TOKEN = "Hidden" start_sequence =…
Ahmad Faraaz
  • 1
  • 1
0
votes
0 answers

How can I implement text classification for the purpose of matching using GPT-3?

I have tried fine tuning a GPT-3 model for the purpose of text classification to classify whether two names match such as 'William Jonathan' and 'William J' and the label would be yes/no, yes indicating that two names are matching and no indicating…
hhalaweh
  • 1
0
votes
1 answer

Why is my addEventListener click event only firing once?

I'm using an addEventListener click event to trigger a new GPT3 request which takes the latest database post as a prompt for text completion. The data is sent to the database through a hidden html form, with the action of the form triggering a php…
James Irwin
  • 1
  • 1
0
votes
1 answer

Combine GPT3 with RASA

I am trying to integrate rasa with gpt3, but not getting the proper response. Can help me out to look at my code and tell me issue. def gpt3(text): response = openai.Completion.create( model="code-cushman-001", # engine="ada", …
subhajit saha
  • 33
  • 4
0
votes
0 answers

openai.error.InvalidRequestError: does not have access to the answers endpoint

When I'm trying to implement the QA system with GPT-3, there is an error occurred: openai.error.InvalidRequestError: Org org-Ilv48EJDyLWiTc2SJWjOnRaM does not have access to the answers endpoint. Reach out to deprecation@openai.com if you have any…
Hu Tianrun
  • 11
  • 3
0
votes
0 answers

GPT-3 made a mistake using numpy and I can't fix it

I used GPT-3 to generate a Neural Network to use in a simple "cell" simulator. When I run the script, I get the following error : *hidden_errors = np.dot(output_errors, self.weights_hidden_to_output.T) File "<__array_function__ internals>", line…
Jacques L'Éventreur
  • 1
  • 1
0
votes
1 answer

Memory usage in transforming fine tuning of GPTJ-6b to HuggingFace format

Following this tutorial using TPUs to fine tune GPTJ has worked well. https://github.com/kingoflolz/mesh-transformer-jax/blob/master/howto_finetune.md Why would the step to transform to huggingface format using to_hf_weights.py have an issue with…
Jonathan Hendler
  • 1,239
  • 1
  • 17
  • 23
0
votes
2 answers

How to output the list of probabilities on each token via model.generate?

Right now I have: model = GPTNeoForCausalLM.from_pretrained(model_name) tokenizer = GPT2Tokenizer.from_pretrained(model_name) input_ids = tokenizer(prompt, return_tensors="pt").input_ids.cuda() gen_tokens = model.generate(input_ids,…
pete
  • 1,878
  • 2
  • 23
  • 43
0
votes
1 answer

OpenAI retrieve file content

Unable to retrieve the content of file uploaded already. Kindly suggest what is going wrong? I have tried for each type of file: search, classification, answers, and fine-tune. Files upload successfully but while retrieving content it shows an…
Saddam
  • 23
  • 1
  • 5
0
votes
1 answer

Choosing a good prompt for GPT-3

I am trying to generate a quiz from a text that look like this: Text: "Mary has little lamb and John has a cow. The lamb is one month old. It eats grass and milk, which Mary brings from the the farm." Keywords: "lamb", "cow", "one month old",…
futuredataengineer
  • 442
  • 1
  • 3
  • 14
1 2 3
…
19 20