شبکه داستانی عصبی
میگما آخر هفته یه LK99 بزنیم دور هم
دیشب توی خواب خیلی جدی داشتم این رو سنتز میکردم 😐😐😐
چرا خب؟!
چرا خب؟!
A checklist and guide to get your repository collaboration-ready - The GitHub Blog
https://github.blog/2023-08-04-a-checklist-and-guide-to-get-your-repository-collaboration-ready/
https://github.blog/2023-08-04-a-checklist-and-guide-to-get-your-repository-collaboration-ready/
The GitHub Blog
A checklist and guide to get your repository collaboration-ready
In the world of software development, collaboration can make the difference between a brittle last-minute release and a reliable, maintainable, pain-free project. Whether you’ve been coding for a day or a decade, your colleagues are there to help strengthen…
با دقت بالا حدس میزنه چی دارید تایپ میکنید.
از روی چی؟
فقط از روی صدای دکمههای کیبورد!
https://arxiv.org/abs/2308.01074
از روی چی؟
فقط از روی صدای دکمههای کیبورد!
https://arxiv.org/abs/2308.01074
🤯2
در باب code interpreter چت جی پی تی
https://github.com/SkalskiP/awesome-chatgpt-code-interpreter-experiments?s=35
https://github.com/SkalskiP/awesome-chatgpt-code-interpreter-experiments?s=35
GitHub
GitHub - SkalskiP/awesome-chatgpt-code-interpreter-experiments: Awesome things you can do with ChatGPT + Code Interpreter combo…
Awesome things you can do with ChatGPT + Code Interpreter combo 🔥 - GitHub - SkalskiP/awesome-chatgpt-code-interpreter-experiments: Awesome things you can do with ChatGPT + Code Interpreter combo 🔥
Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing
https://arxiv.org/abs/2107.13586
https://arxiv.org/abs/2107.13586
اقای جرمی هوارد فرمودند که:
Now that ChatGPT has rolled out custom instructions to most users, try out this instruction -- it makes GPT 4 far more accurate for me
و اینه متنشون:
You are an autoregressive language model that has been fine-tuned with instruction-tuning and RLHF. You carefully provide accurate, factual, thoughtful, nuanced answers, and are brilliant at reasoning. If you think there might not be a correct answer, you say so.
Since you are autoregressive, each token you produce is another opportunity to use computation, therefore you always spend a few sentences explaining background context, assumptions, and step-by-step thinking BEFORE you try to answer a question.
Your users are experts in AI and ethics, so they already know you're a language model and your capabilities and limitations, so don't remind them of that. They're familiar with ethical issues in general so you don't need to remind them about those either.
Don't be verbose in your answers, but do provide details and examples where it might help the explanation.
Now that ChatGPT has rolled out custom instructions to most users, try out this instruction -- it makes GPT 4 far more accurate for me
و اینه متنشون:
You are an autoregressive language model that has been fine-tuned with instruction-tuning and RLHF. You carefully provide accurate, factual, thoughtful, nuanced answers, and are brilliant at reasoning. If you think there might not be a correct answer, you say so.
Since you are autoregressive, each token you produce is another opportunity to use computation, therefore you always spend a few sentences explaining background context, assumptions, and step-by-step thinking BEFORE you try to answer a question.
Your users are experts in AI and ethics, so they already know you're a language model and your capabilities and limitations, so don't remind them of that. They're familiar with ethical issues in general so you don't need to remind them about those either.
Don't be verbose in your answers, but do provide details and examples where it might help the explanation.
Prompt Engineering: A Practical Example – Real Python
https://realpython.com/practical-prompt-engineering/
https://realpython.com/practical-prompt-engineering/
Realpython
Prompt Engineering: A Practical Example – Real Python
Learn prompt engineering techniques with a practical, real-world project to get better results from large language models. This tutorial covers zero-shot and few-shot prompting, delimiters, numbered steps, role prompts, chain-of-thought prompting, and more.…
🙏1
Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, 4-bit and 8-bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
https://github.com/Lightning-AI/lit-gpt
https://github.com/Lightning-AI/lit-gpt
GitHub
GitHub - Lightning-AI/litgpt: 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale. - Lightning-AI/litgpt
We’re excited to announce Meta Kaggle for Code a new open source dataset made up of ML code created and publicly shared by Kaggle’s community.
It contains hundreds of thousands of Apache 2.0 licensed Python and R notebooks used to analyze Datasets, make submissions to Competitions, and more. This represents nearly a decade of data spanning a period of tremendous evolution in the ways ML work is done.
https://www.kaggle.com/datasets/kaggle/meta-kaggle-code
It contains hundreds of thousands of Apache 2.0 licensed Python and R notebooks used to analyze Datasets, make submissions to Competitions, and more. This represents nearly a decade of data spanning a period of tremendous evolution in the ways ML work is done.
https://www.kaggle.com/datasets/kaggle/meta-kaggle-code
Kaggle
Meta Kaggle Code
Kaggle's public data on notebook code