Skip to main content

Questions tagged [gpt]

GPT stands for Generative Pre-trained Transformer. The GPT family of neural network models employs the transformer architecture and represents a significant breakthrough in AI technology, particularly in the area of generative AI applications like ChatGPT. Use this tag for general questions about GPT. On questions about specific GenAI tools, use the more specific tag.

Filter by
Sorted by
Tagged with
1 vote
1 answer
18 views

How can I increase the maximum number of images for a single request with GPT4o on Azure?

I use gpt-4o-2024-05-13 via Azure. By default, the current maximum number of images for a single request is 20, since I get that error otherwise: Error code: 400 - {'error': {'code': 'BadRequest', '...
Franck Dernoncourt's user avatar
0 votes
1 answer
37 views

How to generate RWBY-style teams of characters using an LLM?

If you don't know what I mean by "RWBY-style character teams":. In this series (made/produced by Rooster Teeth) the teams are named like "RWBY" where the team's name are the ...
user56510's user avatar
-1 votes
1 answer
15 views

Do Azure OpenAI Service's content filters depend on the OpenAI GPT models? Or are they independent?

Do Azure OpenAI Service's content filters depend on the OpenAI GPT models? Or are they independent? In other word, does the moderation done by those content filters the same for any GPT model or does ...
Franck Dernoncourt's user avatar
2 votes
0 answers
24 views

Are there any differences between OpenAI models available on OpenAI.com and OpenAI models available on Azure?

I wonder whether there exist any difference between OpenAI models available on OpenAI.com and OpenAI models available on Azure.
Franck Dernoncourt's user avatar
1 vote
0 answers
17 views

Which OpenAI GPT models, if any, allow specifying top_k?

I don't see top_k in the current doc but seems to be mentioned in the past. Which OpenAI GPT models, if any, allow specifying top_k?
Franck Dernoncourt's user avatar
1 vote
1 answer
37 views

Why isn't it generally recommended to alter both the temperature and `top_p` when calling GPT?

I read on platform.openai.com/docs/api-reference/chat/create: We generally recommend altering [the temperature] or top_p but not both. Why isn't it generally recommended to alter both the ...
Franck Dernoncourt's user avatar
-1 votes
1 answer
41 views

How Google's TextFX experiment works?

Link: https://textfx.withgoogle.com/ How can an LLM be trained to perform things like this experiment site does? (Visit the site and you will find out more about these tools.) This is different from ...
user56510's user avatar
-1 votes
0 answers
17 views

Do you use any smart terminals?

Do you use any smart terminals such as Termius, Shell gpt, Interpreter or any other? Do you see any advantages or disadvantages? Do you manage your systems using those?
Flaflapoms's user avatar
2 votes
2 answers
130 views

It is possible to train a GPT model to imitate a fictional character?

It is possible to do so, in a way that it has the characteristics of a fictional character, including the name? For instance could I make the model behave like the goddess Hera?
user56510's user avatar
1 vote
1 answer
33 views

What's GPT-3.5-Turbo-0314? Same as GPT-3.5-Turbo-0301?

I see GPT-3.5-Turbo-0314 in https://chat.lmsys.org/?leaderboard: but I can't find GPT-3.5-Turbo-0314 in the OpenAI docs. The closest model (closest based on dates) I can see in https://platform....
Franck Dernoncourt's user avatar
3 votes
3 answers
84 views

Can GPT models be used for text prediction/autofill?

The title says it all. Can they be used in a way that is not for generation of text based on a prompt, but instead for word suggestions based on the context of previously written text?
user56510's user avatar
1 vote
1 answer
83 views

How does Meta Llama-3 LLM compare against GPT 4, Claude Opus, and Mistral-Large on human evaluations?

https://ai.meta.com/blog/meta-llama-3 compared Meta Llama-3 LLM compare against GPT 3.5, Claude Sonnet and Mistral Medium on human evaluations: They conveniently avoided the state-of-art LLMs, namely ...
Franck Dernoncourt's user avatar
1 vote
1 answer
49 views

Does GPT 4 Turbo perform worse than GPT 4?

GPT 4 Turbo is cheaper and accepts a longer context than GPT 4 (128k vs. 8k or 32k). Does it mean GPT 4 Turbo perform worse than GPT 4? Prices from https://openai.com/pricing:
Franck Dernoncourt's user avatar
-1 votes
1 answer
57 views

Is it possible to use GPT-4 32K directly from OpenAI?

I use GPT-4-32K on poe.com. On poe.com, the use of GPT-4-32K is very restricted. Is it possible to use GPT-4-32K directly from OpenAI as an individual user?
user366312's user avatar
0 votes
0 answers
8 views

Is the `id` returned by Azure OpenAI GPT model sensitive, or can I share it publicly without any issue?

When I call an Azure OpenAI GPT model e.g.: #Note: This code sample requires OpenAI Python library version 1.0.0 or higher. import json import pprint from openai import AzureOpenAI client = ...
Franck Dernoncourt's user avatar
0 votes
0 answers
21 views

Issues driving GPT Builder input from an uploaded file

I have created a custom-GPT using OpenAI's GPT Builder. It is a pretty simple GPT that accepts an entity name and location and it tries to find the homepage URL. Real basic stuff. The stuff works ...
GenAI Philic's user avatar
0 votes
0 answers
31 views

What's the difference between "Tokens per Minute Rate Limit (thousands)" and "Rate limit (Tokens per minute)" in Azure OpenAI?

I deployed GPT-4V on Azure OpenAI. I see: Tokens per Minute Rate Limit (thousands): 10 Rate limit (Tokens per minute): 30000 What's the difference between "Tokens per Minute Rate Limit (...
Franck Dernoncourt's user avatar
0 votes
1 answer
62 views

How can I open a licensed GPT chat like on https://chat.openai.com/ on my own user if I have an API key that is not from my user?

I can already ask questions against GPT4 with an API key that I got from a group license, see a question on my first tests at Stack Overflow How do I run a GPT API shell command in Jupyter Notebook ...
questionto42's user avatar
0 votes
0 answers
31 views

Parallelised GPU training

When training/fine-tuning an LLM model it is necessary to have huge GPU resources (VRAM), as such I was wondering if there was a way in Linux to pool GPU resources if I have, say, 5 separate computers ...
mya205's user avatar
  • 9
0 votes
0 answers
12 views

Training a model to generating application specific configuration

I'm thinking of building a model which can generate application specific configuration file. one example can be a simple dhcp server config in JSON/XML format with user asking "need config file ...
sumeet kumar's user avatar
4 votes
1 answer
175 views

What causes a GPT model to output or leak its training data and how to avoid it?

As shown in the screenshot, the model outputs or leaks what appears to be some of the prompts used to train it. I couldn't reproduce the issue though. There were some other questions I had asked ...
Nav's user avatar
  • 331
0 votes
1 answer
72 views

Is it possible to determine how many unique users there are for a custom GPT?

I’ve created a couple dozen custom OpenAI GPTs. Most are barely used; but a few have good usage numbers. My most used is called Data Science Consultant. Is it possible to know how many people are ...
Christopher Klaus's user avatar
4 votes
1 answer
1k views

How can you get two OpenAI custom GPTs to talk to each other?

I’ve tried specifying the URL of one custom URL GPT in the creation of another custom GPT in an attempt to have a team of custom GPTs working together. That failed… Has anyone found a way to get ...
Christopher Klaus's user avatar
-3 votes
1 answer
3k views

Best realistic story telling LLM?

I've been using WizardLM-SuperCOT30bUncensored for quite some time now, and I'm wondering if there is anything better these days for stories? Because apparently this model is cool, but I can see that ...
Marcin Jasny's user avatar
2 votes
1 answer
128 views

Have we over-hyped the evolution of LLM performance? [closed]

Many brilliant theorists and visionaries, like the great Max Tegmark, have gone to extraordinary lengths to inform the public about the impending reality of AI surpassing human intelligence in the ...
Gabriel Turner's user avatar
0 votes
0 answers
88 views

How to add new mode in chatGPT-4? For example "Advanced Data Analyses"

When I create a new chat, at the top of the chatGPT version selection window a dropdown list of available modes appears when I hover over GPT-4 tab. Right now I only have 3 options: Default, Browse ...
François Esthète's user avatar
1 vote
0 answers
36 views

Get Llama-2 Rotary Embeddings

I want to get the Llama-2 rotary embeddings. I do print(model) and get the following output: In the picture I highlight the rotary embeddings. How can get the rotary embeddings and how can I ...
Christian01's user avatar
1 vote
1 answer
65 views

Can the Use of External Data Sources to Enhance GPT Models Raise Legal Concerns? [closed]

I recently came across news about GPT-BOT being able to read articles from sources like The New York Times and Financial Times, but I've also heard that The New York Times blocked its use. How does ...
Zack DB's user avatar
  • 47
-1 votes
1 answer
184 views

GPT-4 to Generate USMLE Exam Questions

I have a set of example multiple choice questions on the USMLE, a US medical licensing exam. I want to use the set of questions, their answers, and the explanations associated with the correct answers ...
2567655222's user avatar
3 votes
0 answers
113 views

How is the "Corresponding requests per minute (RPM)" calculated when creating a GPT deployment in Azure?

I created an Azure OpenAI resource in my Azure account. I want to deploy a GPT-4-32k model. How is the "Corresponding requests per minute (RPM)" calculated when creating a GPT deployment in ...
Franck Dernoncourt's user avatar
1 vote
0 answers
279 views

How to use GPT-4 to help authors write a document with LaTeX formatting?

I read in OpenAI's GPT-4 Technical Report: GPT-4 was used in the following ways: to help us iterate on LaTeX formatting [...] How can one use GPT-4 to help authors iterate on LaTeX formatting? Note ...
Franck Dernoncourt's user avatar
-2 votes
1 answer
102 views

When I use content generated by an algorithm, do I legally have to cite the source(s)? [closed]

Let's say that I used ChatGPT to write the text of an article and Stable Diffusion to create an image and include it in the article. Do I have to credit ChatGPT, Stable Diffusion, and the authors of ...
A.L - say no to AI's user avatar
5 votes
2 answers
795 views

Does Llama2 LLMs have real time data?

Meta released their open source LLM, Llama 2. Does Llama 2 have real time data or this was trained on data available till some date?
Rashid's user avatar
  • 179
7 votes
9 answers
12k views

How to generate structured data like JSON with LLM models?

I'm currently working on a project that requires the generation of complex JSON documents using Large Language Models (LLMs). These documents, representing rich text content, can contain various ...
Léonard Henriquez's user avatar
5 votes
1 answer
333 views

Prompt engineering GPT for numerical scores?

Background: I am currently working on an NLP project using GPT 3.5 via the OpenAI python API. Engineering good prompts seems to be the most critical part of my pipeline so far. Crucially I have long ...
user avatar
78 votes
6 answers
56k views

How to get ChatGPT to Stop Apologizing?

Is there a way to stop ChatGPT from excessively apologizing, when challenged, even when ChatGPT is correct in its reply? ChatGPT will start apologizing and start the replies with sentences like: I ...
Arbel's user avatar
  • 871
2 votes
2 answers
414 views

What is the exact number of web pages used to train ChatGPT-3.5, and what methods are employed to filter out inaccurate information?

What is the total number of web pages used to train ChatGPT-3.5, and what methods are employed to ensure the veracity of the vast data while filtering out inaccurate information?
Zack DB's user avatar
  • 47
10 votes
4 answers
6k views

Can you have ChatGPT 4 "explain" how it generated an answer?

While I understand that GPT-4 does not use logic in the same way that a human does, is there some way to have ChatGPT "explain" itself?
dave20's user avatar
  • 119
9 votes
2 answers
1k views

Is there an offline GPT model I can use to generate narrative reports from excel data based on an existing set of files?

I have a large excel spreadsheet containing data that I have used to write many narrative reports. Without knowing a ton about the technical side of GPT models it seems like it would be theoretically ...
VanHammersly's user avatar
14 votes
3 answers
2k views

Are there powerful text generators that preserve attribution?

Traditional text generation works by playing a big game of Mad Libs. (A famous example is the Dada Engine, used in the Postmodernism Generator.) You could, if you so chose, go in and track down the ...
wizzwizz4's user avatar
  • 420
2 votes
2 answers
754 views

Why does ChatGPT always reply with a conversation to the word "example"?

When asking ChatGPT, Example It usually replies with a conversation between two people. Examples: Beach Trip Planning Person A: Hi there! How was your weekend? Person B: Hello! My weekend was ...
Ghost's user avatar
  • 131
3 votes
1 answer
255 views

To what extent can GenAI be used for content moderation?

I've seen several people trying to use GenAI technologies for content moderation. This doesn't seem impossible, on the face of it: I use regular expressions to great effect, and I can see how more ...
wizzwizz4's user avatar
  • 420
8 votes
2 answers
948 views

If I use a GPT add-on in my spreadsheet, is my data still private, or can it be leaked to other GPT users?

I use spreadsheets a lot. Some of my spreadsheets have student details like school, classroom, name, age, parent names, etc. Other spreadsheets have different data sets but also contain sensitive data ...
Wicket's user avatar
  • 1,012
8 votes
3 answers
730 views

What's the difference between the terms "ChatGPT", "GPT", "GPT-4", and "GPT-3.5-turbo"?

I often chat with the various bots at Poe.com. We see bots such as: ChatGPT: Powered by gpt-3.5-turbo. GPT-4: OpenAI's most powerful model. Stronger than ChatGPT in quantitative questions (math and ...
Rebecca J. Stones's user avatar