151–160 of 185 posts
Earlier quoted context omitted.
Train it on what? I want host our own AI, have it injest our docs, and answer questions about them. What is the best tool today to do that?
GPT4 + retrieval might be the fastest path. But quality not guaranteed, and assuming you do not mind uploading all your private info to openAI. This project might be the best option where you can finetune an LLM on your data and keep the model yourself
> In our first release, we will share the training, serving, and evaluation code. We plan to release the model weights by providing a version of delta weights that build on the original LLaMA weights, but we are still figuring out a proper way to do so. Join our Discord server and follow our Twitter to get the latest updates. Please correct me if I'm wrong, but it seems like this is not actually an open-source model?…
I am a Vicuna developer. We plan to release the weights once we have addressed all concerns and have a low-resource version of the inference code ready. We released the demo first to get some early feedback on the model.
Or is this work "transferable" to other LLMs, once they become available?
It's hilarious to see how these models can hallucinate stuff that doesn't exist... Q: What is the meaning of ABBA's song "I have a dream"? A: "I Have a Dream" is a song by the Swedish pop group ABBA, released in 1970. The song was written by Benny Andersson and Björn Ulvaeus, and it was the group's first hit single. The song is a ballad that talks about a person's dream of finding love and happiness. The lyrics descr…
Chat implementations provide your recent back and forth history as example to the next prompt. This is how providing an example reply in JSON can get it to reply with new data using JSON.
Ongoing replies reference what it interprets as labels (the blanks to fill in) provided in the examples, replacing those tokens with new tokens.
Look at your first question and second question again. Pretend the first reply is in JSON but with placeholders for song title, artists, topic, lyrical analysis, and critique.
Pretend the second reply was supposed to use the first reply as its example, and replace only new data.
You see it put new generation into the provided example structure.
Now you can see what it did there. It did exactly what you prompted it to do.
It's hilarious to see how these models can hallucinate stuff that doesn't exist... Q: What is the meaning of ABBA's song "I have a dream"? A: "I Have a Dream" is a song by the Swedish pop group ABBA, released in 1970. The song was written by Benny Andersson and Björn Ulvaeus, and it was the group's first hit single. The song is a ballad that talks about a person's dream of finding love and happiness. The lyrics descr…
Q1: A: ABBA's "I Have a Dream" is a song from their 1979 album, "Voulez-Vous." The song's lyrics express themes of hope, self-belief, and optimism...
Q2: A:ABBA does not have a song called "General Trouble" in their discography. It's possible that you may be referring to a different artist or misremembering the title of the song. If you could provide more information or the correct title, I would be happy to help you understand the meaning behind the song.
Earlier quoted context omitted.
I also asked about a recipe with mushrooms, tea, and dishwasher soap. It happily gave me one... mentioning at some point "Add the dishwasher soap to the tea, if desired. The soap will help to release the flavor of the mushrooms and give the tea a slightly soapy taste."
Presumably dishwasher soap is somewhat edible or it would not be on dishes? So it might actually be correct just weird, but it's what you ordered
Earlier quoted context omitted.
Asking a token-based LM to generate only tokens that contain the letter "Z" is... well. Like asking someone who prepared a speech to smoothly skip all words with "ei" in them. The LM would basically need to have memorized the set of letters that each of its token stands for, from the training data. I'm surprised it works at all.
It would be nice if it would tell you when you are asking it something that it is not designed to answer
The work being done with Llama and Alpaca and so on is what I've found to be most interesting in the past few weeks. The fact that we are capable of producing such high quality conversational models that we can actually get to freely experiment with is really encouraging. I'm particularly excited about applications such as viper[1] and other forms of plugins as well as model ensembles. [1] https://viper.cs.columbia.e…
Here's an example I just had:
Q: What should I do for my wife today?
A: There are many things you can
> In our first release, we will share the training, serving, and evaluation code. We plan to release the model weights by providing a version of delta weights that build on the original LLaMA weights, but we are still figuring out a proper way to do so. Join our Discord server and follow our Twitter to get the latest updates. Please correct me if I'm wrong, but it seems like this is not actually an open-source model?…
I am a Vicuna developer. We plan to release the weights once we have addressed all concerns and have a low-resource version of the inference code ready. We released the demo first to get some early feedback on the model.