gpt-neo
sharegpt
gpt-neo | sharegpt | |
---|---|---|
82 | 37 | |
6,158 | 1,680 | |
- | - | |
7.3 | 6.9 | |
about 2 years ago | 6 months ago | |
Python | TypeScript | |
MIT License | MIT License |
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.
gpt-neo
-
How Open is Generative AI? Part 2
By December 2020, EleutherAI had introduced The Pile, a comprehensive text dataset designed for training models. Subsequently, tech giants such as Microsoft, Meta, and Google used this dataset for training their models. In March 2021, they revealed GPT-Neo, an open-source model under Apache 2.0 license, which was unmatched in size at its launch. EleutherAI’s later projects include the release of GPT-J, a 6 billion parameter model, and GPT-NeoX, a 20 billion parameter model, unveiled in February 2022. Their work demonstrates the viability of high-quality open-source AI models.
-
Creating an open source chat bot like ChatGPT for my own dataset without GPU?
Yeah, if that is your requirement you should definitely ignore chatterbot, as its older and probably not what your teacher wants. I'm looking at the gpt-neo docs right now: https://github.com/EleutherAI/gpt-neo
-
Any real competitor to GPT-3 which is open source and downloadable?
3.) EleutherAI's GPT-Neo and GPT-NeoX: EleutherAI is an independent research organization that aims to promote open research in artificial intelligence. They have released GPT-Neo, an open-source language model based on the GPT architecture, and are developing GPT-NeoX, a highly-scalable GPT-like model. You can find more information on their GitHub repositories: GPT-Neo: https://github.com/EleutherAI/gpt-neo GPT-NeoX: https://github.com/EleutherAI/gpt-neox
-
⚡ Neural - AI Code Generation for Vim
This is one of the first comprehensive plugins that has been rewritten to support multiple AI backends such as OpenAI GPT3+ and other custom sources in the future such as ChatGPT, GPT-J, GPT-neo and more.
-
Looks like some Taliban fighters are getting burnt out working the 9-5 grind
GPT-Neo is newer than GPT-2 on the open source side of things. In my experience, it tends to give longer and more creative responses than GPT-2 but not on the level of GPT-3. I've not tried GPT-J or GPT-NeoX, but they're also open source and reportedly better than GPT-Neo (albeit less accessible).
- H3 - a new generative language models that outperforms GPT-Neo-2.7B with only *2* attention layers! In H3, the researchers replace attention with a new layer based on state space models (SSMs). With the right modifications, they find that it can outperform transformers.
- First Open Source Alternative to ChatGPT Has Arrived
-
Where is the line for AI and where does ChatGPT stand?
Finally, yes-- it is trained via masked language modeling (text prediction). The approach has been fairly standard for years- the big difference with the GPT* models is the number of paramaters and volume of text-- we still haven't reached a ceiling with LLM parameters- they appear to keep improving with size. This training allows the model to learn a strong representation of language. Their training approach is published and open-source GPT* versions have already been made and released (https://github.com/EleutherAI/gpt-neo). However, the models are huge and can't be run locally for hobbyists. This gets at larger issues in democratization of ML.
- Using the GPT-3 AI Writer inside Obsidian(This is COOL)
-
Teaser trailer for "The Diary of Sisyphus" (2023), the world's first feature film written by an artificial intelligence (GPT-NEO) and produced Briefcase Films, my indie film studio based in Northern Italy
- GPT-Neo 2.7B, released Mar/2021, and unmaintained/unsupported as of Aug/2021? or;
sharegpt
-
How Open is Generative AI? Part 2
Vicuna is another instruction-focused LLM rooted in LLaMA, developed by researchers from UC Berkeley, Carnegie Mellon University, Stanford, and UC San Diego. They adapted Alpaca’s training code and incorporated 70,000 examples from ShareGPT, a platform for sharing ChatGPT interactions.
-
create the best coder open-source in the world?
We can say that a 13B model per language is reasonable. Then it means we need to create a democratic way for teaching coding by examples and solutions and algorithms, that we create, curate and use open-source. Much like sharegpt.com but for coding tasks, solutions ways of thinking. We should be wary of 'enforcing' principles rather showing different approaches, as all approaches can have advantages and disadvantages.
-
Thank you ChatGPT
You can see the url in the comment, https://sharegpt.com and if you go there it gives you the option for installing the chrome extension, after that it shouldn’t be hard to use it
- The conversation started as what would AI do if it became self aware and humans tried to shut it down. The we got into interdimensional beings. Most profound GPT conversation I have had.
-
Übersicht aller nützlichen Links für ChatGPT Prompt Engineering
ShareGPT - Share your prompts and your entire conversations
-
(Reverse psychology FTW) Congratulations, you've played yourself.
Or used https://sharegpt.com
-
"Prompt engineering" is easy as shit and anybody who tells you otherwise is a fucking clown.
you can gets lots of ideas here > https://sharegpt.com/ (180,000+ prompts)
-
I built a ChatGPT Mac app in just 20 minutes with no coding experience - thanks ChatGPT!
I would love to read the whole conversation: Check out this cool little GPT sharing extension: https://sharegpt.com - that way the code snippets can be copied easily
-
Teaching ChatGPT to Speak My Son’s Invented Language
> Cool, that’s really the only point I’m making.
To be clear, I'm saying that I don't know if they are, not that we know that it's not the same.
It's not at all clear that humans do much more than "that basic token sequence prediction" for our reasoning itself. There are glaringly obvious auxiliary differences, such as memory, but we just don't know how human reasoning works, so writing off a predictive mechanism like this is just as unjustified as assuming it's the same. It's highly likely there are differences, but whether they are significant remains to be seen.
> Not necessarily scaling limitations fundamental to the architecture as such, but limitations in our ability to develop sufficiently well developed training texts and strategies across so many problem domains.
I think there are several big issues with that thinking. One is that this constraint is an issue now in large part because GPT doesn't have "memory" or an ability to continue learning. Those two need to be overcome to let it truly scale, but once they are, the game fundamentally changes.
The second is that we're already at a stage where using LLMs to generate and validate training data works well for a whole lot of domains, and that will accelerate, especially when coupled with "plugins" and the ability to capture interactions with real-life users [1]
E.g. a large part of human ability to do maths with any kind of efficiency comes down to rote repetition and generating large sets of simple quizzes for such areas is near trivial if you combine an LLM at tools for it to validate its answers. And unlike with humans where we have to do this effort for billions of humans, once you have an ability to let these models continue learning you make this investment in training once (or once per major LLM effort).
A third is that GPT hasn't even scratched the surface in what is available in digital collections alone. E.g. GPT3 was trained on "only" about 200 million Norwegian words (I don't have data for GPT4). Norwegian is a tiny language - this was 0.1% of GPT3's total corpus. But the Norwegian National Library has 8.5m items, which includes something like 10-20 billion words in books alone, and many tens of billions more in newspapers, magazines and other data. That's one tiny language. We're many generations of LLM's away from even approaching exhausting the already available digital collections alone, and that's before we look at having the models trained on that data generate and judge training data.
[1] https://sharegpt.com/
-
Humans in Humans Out: GPT Converging Toward Common Sense in Both Success/Failure
of that conversation. Perhaps something like shareGPT[1] can help?
[1] https://sharegpt.com
What are some alternatives?
gpt-neox - An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.
ChatGPT - Lightweight package for interacting with ChatGPT's API by OpenAI. Uses reverse engineered official API.
haystack - :mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
llm-workflow-engine - Power CLI and Workflow manager for LLMs (core package)
openchat - OpenChat: Easy to use opensource chatting framework via neural networks
unofficial-chatgpt-api - This repo is unofficial ChatGPT api. It is based on Daniel Gross's WhatsApp GPT
tensorflow - An Open Source Machine Learning Framework for Everyone
openai-python - The official Python library for the OpenAI API
mesh-transformer-jax - Model parallel transformers in JAX and Haiku
chatgpt-conversation - Have a conversation with ChatGPT using your voice, and have it talk back.
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
langchain - ⚡ Building applications with LLMs through composability ⚡ [Moved to: https://github.com/langchain-ai/langchain]