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
2
votes
1 answer

gpt3 fine tuning with openai not learning

For my fine tuning jsonl files, I wanted a model that could predict the gender of the speaker given a statement. For instance, the prompt: "i went to buy a skirt today" has completion as "female". I created several examples and gave it to gpt3 to…
user19404912
2
votes
1 answer

Gpt 3 keywords extractor

I'm getting accustomed to gpt and want to build a keywords extractor for book summaries. Can someone point me to the references that'd help for my use case ?
user15181966
  • 21
  • 1
  • 4
2
votes
1 answer

TypeError: Cannot subclass while fine tuning GPT-J

I am trying to fine tune GPT-J by following this GitHub Repository. When running the training command, I encounter this error: Traceback (most recent call last): File "device_train.py", line 13, in from mesh_transformer import util …
lowkey
  • 140
  • 10
2
votes
0 answers

Uncaught RangeError [MESSAGE_CONTENT_TYPE]: Message content must be a non-empty string

I am trying to make a gpt3 chatbot but I keep getting this error on Discord.js v11. [Uncaught RangeError [MESSAGE_CONTENT_TYPE]: Message content must be a non-empty string.] client.on("messageCreate", function (message) { if…
2
votes
1 answer

OpenAI GPT3 Search API not working locally

I am using the python client for GPT 3 search model on my own Jsonlines files. When I run the code on Google Colab Notebook for test purposes, it works fine and returns the search responses. But when I run the code on my local machine (Mac M1) as a…
A I
  • 63
  • 5
2
votes
2 answers

AttributeError: module transformers has no attribute TFGPTNeoForCausalLM

I cloned this repository/documentation https://huggingface.co/EleutherAI/gpt-neo-125M I get the below error whether I run it on google collab or locally. I also installed transformers using this pip install…
Nicole Douglas
  • 579
  • 4
  • 14
1
vote
1 answer

When using GPT-4 API, do I need to send the entire conversation back each time?

I'm new to OpenAI API. I work with GPT-3.5-Turbo, using this code: messages = [ {"role": "system", "content": "You’re a helpful assistant"} ] while True: content = input("User: ") if content == 'end': …
Realchini
  • 11
  • 2
1
vote
1 answer

Async function calling gpt

`import json import requests import openai OPENAI_KEY = "XXX" openai.api_key = 'XXX' GPT_MODEL = "gpt-3.5-turbo-0613" def chat_completion_request(messages, functions=None, function_call=None, model=GPT_MODEL): headers = { …
1
vote
0 answers

PHP - Having a long conversation with GPT 3.5 API

I am using GPT 3.5 Chat Completion API to write a 2000 words article, but it produces only about 1000 words response regardless of the topic. So I am trying to get it to write one half of the article in 1000 words at a time, but it only responds…
Grey Lover
  • 31
  • 1
  • 1
  • 11
1
vote
2 answers

Why do I get the error "Unrecognized request argument supplied: functions" when using `functions` when calling Azure OpenAI GPT?

I'm trying to use functions when calling Azure OpenAI GPT, as documented in https://platform.openai.com/docs/api-reference/chat/create#chat/create-functions I use: import openai openai.api_type = "azure" openai.api_base =…
Franck Dernoncourt
  • 77,520
  • 72
  • 342
  • 501
1
vote
1 answer

Cant find GPT3.5-Turbo-16k on OpenAI Azure

I'm trying to deploy a GPT3.5-Turbo-16k model in Azure (in theory, already available, as announced by Microsoft), but i can't find it in the options, as shown in the image. Deploying a model in Azure: Im using East US with Standard pricing tier. I…
1
vote
1 answer

OpenAI gpt-3.5-turbo: Request failed with status code 400

does this method in node.js doesn't work anymore? Because back then it was working fine but now it doesn't work anymore and also this code is also based on their official docs which is this…
1
vote
1 answer

My JavaScript chatgpt openai implementation keeps giving me an HTTP 429

Below is my code... and I am looking at the API usage on the openai console and I am way under the limit. I haven't ever been able to get a sucessful response. I am copying the code from their documentation. I keep getting a HTTP 429 const…
steve landiss
  • 1,833
  • 3
  • 19
  • 30
1
vote
1 answer

How to get more detailed results sources with Langchain

I am trying to put together a simple "Q&A with sources" using Langchain and a specific URL as the source data. The URL consists of a single page with quite a lot of information on it. The problem is that RetrievalQAWithSourcesChain is only giving me…
GSouth
  • 15
  • 1
  • 4
1
vote
1 answer

AuthenticationError: in OpenAPI api

I have been trying to use langchain library's ChatOpenAI, I pip installed langchain, and imported ChatOpenAI I'm running my code on colab so I set my the openAI's api key as: %env OPENAI_API_KEY= my_api_key now when I try to initialize ChatOpenAI…
Sinan
  • 77
  • 6