Alpaca-LoRA with Docker
github.com
Alpaca-LoRA with Docker
1–10 of 31 posts
Re: Alpaca-LoRA with Docker
#2This is neat and all but both Alpaca and Lora are things I already use and already read about on HN, except now their names are bulldozed by LLM tech and things will never be the same.
Re: Alpaca-LoRA with Docker
#3This says "We provide an Instruct model of similar quality to text-davinci-003", but two paragraphs later says the output is comparable to Stanford's Alpaca. Those seem like very different claims.
Re: Alpaca-LoRA with Docker
#4What is the final size of the weights?
Re: Alpaca-LoRA with Docker
#5This says "We provide an Instruct model of similar quality to text-davinci-003", but two paragraphs later says the output is comparable to Stanford's Alpaca. Those seem like very different claims.
"We performed a blind pairwise comparison between text-davinci-003 and Alpaca 7B, and we found that these two models have very similar performance: Alpaca wins 90 versus 89 comparisons against text-davinci-003."
Re: Alpaca-LoRA with Docker
#6The demo on HuggingFace with the pre trained mode doesn’t seem that good.
Although better than Bard (btw, Bard sucks compared to ChatGPT and can’t even do translations - which I would have expected out of the box from Google)
Re: Alpaca-LoRA with Docker
#7This is neat and all but both Alpaca and Lora are things I already use and already read about on HN, except now their names are bulldozed by LLM tech and things will never be the same.
Just run all your web browsing through GTP and tell it to differentiate them for you
Re: Alpaca-LoRA with Docker
#8The demo on HuggingFace with the pre trained mode doesn’t seem that good. Although better than Bard (btw, Bard sucks compared to ChatGPT and can’t even do translations - which I would have expected out of the box from Google)
It’s worth noting this is the 7B model (nonquantized). You can get this running on pretty much any GPU with 8GB VRAM and above. You can run the 13B model but that would take two GPU or reducing FP16 to FP8 (I haven’t tried it myself). A single connection for chatgpt is rumored to require 8X A100.
Re: Alpaca-LoRA with Docker
#9That name is so unfortunate. Nobody searched “Lora” before picking it. Bit of a blunder if you ask me.
Re: Alpaca-LoRA with Docker
#10From the repo README:
> Try the pretrained model out here, courtesy of a GPU grant from Huggingface!
https://huggingface.co/spaces/tloen/alpaca-lora
Anyone else getting error messages when trying to submit instructions to the model on Huggingface? It just says "Error" so I don't know if it's a "too many users" problem or something else
edit: nevermind, I was able to get a response after a few more tries, plus a 20 second processing time