promptbench
awesome-gpt-prompt-engineering
promptbench | awesome-gpt-prompt-engineering | |
---|---|---|
4 | 18 | |
2,103 | 811 | |
9.0% | - | |
9.2 | 6.6 | |
12 days ago | 6 days ago | |
Python | Python | |
MIT License | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
promptbench
-
Show HN: Times faster LLM evaluation with Bayesian optimization
Fair question.
Evaluate refers to the phase after training to check if the training is good.
Usually the flow goes training -> evaluation -> deployment (what you called inference). This project is aimed for evaluation. Evaluation can be slow (might even be slower than training if you're finetuning on a small domain specific subset)!
So there are [quite](https://github.com/microsoft/promptbench) [a](https://github.com/confident-ai/deepeval) [few](https://github.com/openai/evals) [frameworks](https://github.com/EleutherAI/lm-evaluation-harness) working on evaluation, however, all of them are quite slow, because LLM are slow if you don't have infinite money. [This](https://github.com/open-compass/opencompass) one tries to speed up by parallelizing on multiple computers, but none of them takes advantage of the fact that many evaluation queries might be similar and all try to evaluate on all given queries. And that's where this project might come in handy.
- FLaNK Weekly 31 December 2023
- FLaNK 25 December 2023
- Promptbench: A Unified Library for Evaluating and Understanding LLMs
awesome-gpt-prompt-engineering
-
Chatgpt got me my dream job right out of college
1) https://github.com/snwfdhmp/awesome-gpt-prompt-engineering 2) https://www.europe.study/artificial-intelligence?twclid=273rg3p5g5umnt3g3ifxzysbin 3) https://coursera.org/projects/chat-gpt-for-beginners-using-ai-for-market-research
- Community Curated Prompt Engineering Resources
-
Is GPT prompt engineering now a real job?
GitHub link to an extensive list of GPT prompt engineering tools, for everyone who wants to educate themselves more: https://github.com/snwfdhmp/awesome-gpt-prompt-engineering
-
Becoming a prompt engineer
This is the most complete so far https://github.com/snwfdhmp/awesome-gpt-prompt-engineering
-
Are there paid courses that are worth getting from an employment standpoint? Certs? Other accreditation?
While paid courses and certifications can certainly be beneficial, there's also a wealth of knowledge available for free, especially from the open-source community. For instance, I've been working on a repository called Awesome GPT Prompt Engineering that could be of interest to you.
-
Awesome list of Prompt Engineering techniques, guides & tutorials
I'm an open source software developer and i want to share all things i learn about prompt engineering.
I'm currently working on a project called awesome-gpt-prompt-engineering and I'm actively seeking collaborators who are interested in contributing to this exciting initiative.
-
Keywordin’
Absolutely, I'm always up for sharing and learning together! I've been working on this GitHub repository called awesome-gpt-prompt-engineering. It's actually my own repository, and it's all about creating effective prompts for GPT models.
-
Help in Generating prompt for tagging sources along with answers
To tackle this task, you can leverage the power of GPT-based models combined with some prompt engineering. I've actually been working on a project that might be helpful for you. I've created an open-source repository called "awesome-gpt-prompt-engineering" (you can find it here), which provides various techniques and strategies for enhancing prompts to improve model performance.
-
Unleashing the Power of GPT Prompt Engineering: A Deep Dive into the Awesome GPT Prompt Engineering Project
Hello, fellow developers and AI enthusiasts! I'm snwfdhmp, a programmer with a passion for exploring the frontiers of AI and machine learning. Today, I want to share with you a project that I've been working on: Awesome GPT Prompt Engineering. It's a curated list of resources, tools, and other shiny things for GPT prompt engineering.
What are some alternatives?
osgameclones - Open Source Clones of Popular Games
LLM-Prompt-Library - Advanced Code and Text Manipulation Prompts for Various LLMs. Suitable for GPT-4, Claude, Llama3, Gemini, and other high-performing open-source LLMs.
opencompass - OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
botbots - A dataset featuring diverse dialogues between two ChatGPT (gpt-3.5-turbo) instances with system messages written by GPT-4. Covering various contexts and tasks (task-oriented dialogue systems, abstract reasoning, brainstorming).
JavaOnRaspberryPi - Sources and scripts for the book "Getting started with Java on the Raspberry Pi"
Awesome-Prompt-Engineering - This repository contains a hand-curated resources for Prompt Engineering with a focus on Generative Pre-trained Transformer (GPT), ChatGPT, PaLM etc
Zolver - Automatic jigsaw puzzle solver
promptflow - Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.
FLiPStackWeekly - FLaNK AI Weekly covering Apache NiFi, Apache Flink, Apache Kafka, Apache Spark, Apache Iceberg, Apache Ozone, Apache Pulsar, and more...
GPT-4-Prompt-Library - Advanced Code and Text Manipulation Prompts for Various LLMs. Suitable for GPT-4, Claude, Llama2, Falcon, Bard, and other high-performing open-source LLMs. [Moved to: https://github.com/abilzerian/LLM-Prompt-Library]
Stirling-PDF - #1 Locally hosted web application that allows you to perform various operations on PDF files
tree-of-thoughts - Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%