The A.I Megathread (LLM , GPT , Development)
GitHub - togethercomputer/OpenChatKit
Contribute to togethercomputer/OpenChatKit development by creating an account on GitHub.
github.com
snippet:
Strengths of the model
There are several tasks that OpenChatKit excels at out of the box. This includes:- Example 1: Summarization and question answering within context.
Code:**Summarize a long document into a single sentence and conduct question answering related to the document, with multiple rounds** <human>: Last year, the travel industry saw a big rebound in demand — and that demand is showing no signs of slowing down this spring break travel season. Planes and hotels will be full, travelers will likely face long queues, cancellations, massive crowds and plenty of other travel nightmares. But perhaps the most frustrating thing you’ll have to prepare for this spring break is if your luggage goes missing. You’ve got to somehow track down your belongings that were in the airline’s care and then wait to be reunited — all while trying to enjoy the start of your long-awaited vacation. As far as travel nightmares go, lost luggage is up there as one of the worst. To be honest up front, I am great at strategically losing things — or rather, losing stuff with style. (I hope you appreciate the “Toy Story” reference.) So when a product comes along that’s a perfect way to keep track of my belongings — especially when traveling — I’m adding it to my travel bag. I’ve been a big fan of Apple’s $29 item tracker, dubbed AirTag. The long-rumored AirTag product finally launched in 2021, and while it’s not the first item tracker to exist, it has two key features that set it apart from the rest to make it the ultimate travel companion: access to the Find My network and Precision Finding technology. The Federal Aviation Administration has even ruled that having an AirTag in your luggage is permitted and, in fact, not a safety hazard. The devices only contain 0.1 grams of lithium, which falls below the FAA’s limit. “Luggage tracking devices powered by lithium metal cells that have 0.3 grams or less of lithium can be used on checked baggage,” the FAA said in a statement. “Apple AirTags meet this threshold; other luggage tracking devices may not.” But, you may be wondering what makes them so special and why you should carry one in your checked luggage this spring break? Let’s explain why. Summarize the above into a single paragraph. <bot>: If you're traveling this spring break, you might want to consider investing in an item tracker to help you find your lost luggage. Apple's AirTag is the best option, according to a new report. <human>: But isn't it unsafe to put AirTag in a luggage? <bot>: The Federal Aviation Administration has ruled that having an AirTag in your luggage is permitted and, in fact, not a safety hazard. <human>: Ah, why is that? <bot>: The devices only contain 0.1 grams of lithium, which falls below the FAA’s limit.
- Example 2: Extraction.
Code:**Extract structured information from unstructured documents, as illustrated in the following example.** <human>: Generate a table summarizing the options outlined in this email. Team, we have to make a decision on the product plan for Goocrux v2. The first option will take us 3 weeks of development, and will achieve performance of 80ms, but means that the UI has to change. The second option will take us 4 weeks of development, and will achieve performance of 60ms, without any UI change. The third option will take the longest -- 6 weeks of development, will achieve performance of 30ms, without any UI change. A markdown table with four columns: (1) Option ID, (2) Development time, (3) Performance, (4) UI Change: <bot>: #. | ID | Option ID | Development time | Performance | UI Change | | --------- | --------- | --------- | --------- | --------- | | 1 | 1 | 3 weeks | 80ms | Yes | | 2 | 2 | 4 weeks | 60ms | No | | 3 | 3 | 6 weeks | 30ms | No |
- Example 3: Classification.
Code:**Classifying a sentence or paragraph into different categories.** <human>: Classify the sentiment of the following sentence into Positive, Neutral, or Negative: Super excited about teaching Stanford’s first course on Large Language Models! Check the syllabus out here <bot>: Positive <human>: Classify the sentiment of the following sentence into Positive, Neutral, or Negative: How about the following sentence: It is raining outside and I feel so blue <bot>: Negative
Weaknesses of the model
That said, there are several areas where we have more work to do, and we need your help! Some of these include:- Knowledge-based closed question and answering: The chatbot may hallucinate and give incorrect results. Be sure to fact check, and if possible provide feedback with the corrected information.
- Coding tasks: The chatbot was not trained on a large enough corpus of source code to excel at writing code. We welcome contributions of additional datasets to improve this!
- Repetition: Sometimes the chatbot will repeat its response. We’re working to improve this, but in the meantime you can click the refresh button to start a new conversation.
- Context switching: If you change the topic in the middle of a conversation the chatbot often cannot make the switch automatically and will continue to give answers related to the prior topic.
- Creative writing and longer answers: The chatbot does not generate long, creative text such as an essay or story.
Uses
Direct Use
The model is intended for research purposes. Possible research areas and tasks include- Safe deployment of models which have the potential to generate harmful content.
- Probing and understanding the limitations and biases of dialogue models or language models.
- Generation of artworks and use in design and other artistic processes.
- Applications in educational or creative tools.
- Research on dialogue models or language models.
GitHub - ggerganov/llama.cpp: Port of Facebook's LLaMA model in C/C++
Port of Facebook's LLaMA model in C/C++. Contribute to ggerganov/llama.cpp development by creating an account on GitHub.
github.com
Last edited:
SadimirPutin
Superstar
commenting to come back to it later
nebullvm/apps/accelerate/chatllama at main · nebuly-ai/nebullvm
Plug and play modules to optimize the performances of your AI systems 🚀 - nebullvm/apps/accelerate/chatllama at main · nebuly-ai/nebullvm
github.com
ChatLLaMA
ChatLLaMAPlease note this library does NOT contain LLaMA’s weights; to access the weights, you need to apply to Meta's form.
is a library that allows you to create hyper-personalized ChatGPT-like assistants using your own data and the least amount of compute possible. Instead of depending on one large assistant that “rules us all”, we envision a future where each of us can create our own personalized version of ChatGPT-like assistants. Imagine a future where many ChatLLaMAs at the "edge" will support a variety of human's needs. But creating a personalized assistant at the "edge" requires huge optimization efforts on many fronts: dataset creation, efficient training with RLHF, and inference optimization.This library is meant to simplify the development of hyper-personalized ChatLLaMA assistants. Its purpose is to give develo
Stable Diffusion Browser
Browse, search, and manage all AI generated images on your machine, in one place.
Browse, search, and manage all AI generated images on your machine, in one place.
Announcing GPT-4, a large multimodal model, with our best-ever results on capabilities and alignment
GPT-4
openai.com
GPT-4 can solve difficult problems with greater accuracy, thanks to its broader general knowledge and problem solving abilities.