Settings

Theme

ChatGPT-J: The Privacy-First, Self-Hosted Chatbot Built on GPT-J's Powerful AI

colab.research.google.com

54 points by jarrell_mark 3 years ago · 9 comments

Reader

two_handfuls 3 years ago

"Privacy-First", but also working in a colab notebook - meaning running on someone else's machine? That doesn't seem very private.

serendipty01 3 years ago

Github repo : https://github.com/jarrellmark/chatgpt-j

johntash 3 years ago

Can this be run locally without beefy GPUs by any chance?

  • quesomaster9000 3 years ago

    ggml (https://github.com/ggerganov/ggml) has a GPT-J example, the 6B parameter model runs happily on the CPU 16gb of ram and 8 cores at a couple of words per second, no GPUs necessary.

        gptj_model_load: ggml ctx size = 13334.86 MB
        gptj_model_load: memory_size =  1792.00 MB, n_mem = 57344
        gptj_model_load: model size = 11542.79 MB / num tensors = 285
        main: number of tokens in prompt = 12
    
        An example of GPT-J running on the CPU is shown in Fig. [4](#Fig4
    
        main: mem per token = 16179460 bytes
        main:     load time =  7463.20 ms
        main:   sample time =     3.24 ms
        main:  predict time =  4887.26 ms / 232.73 ms per token
        main:    total time = 13203.91 ms
  • jerpint 3 years ago

    There have been CPU implementations of LLAMA (7b parameters, comparable in size) with very impressive performance

  • ops 3 years ago

    I haven't used this yet, but I am currently running GPT-J on my Mac Studio, so I suspect so.

  • jarrell_markOP 3 years ago

    It should work with about 12gb GPU RAM.

    I got it to load on a GTX 1070 with 8GB GPU RAM, but then it crashed before it could generate a response.

    It needs less RAM than regular GPT-J because the weights are converted to 8-bit

Keyboard Shortcuts

j
Next item
k
Previous item
o / Enter
Open selected item
?
Show this help
Esc
Close modal / clear selection