Code Monkey home page Code Monkey logo

Comments (3)

danielkuhlwein avatar danielkuhlwein commented on August 30, 2024 10

In the end I was able to finally get it working with this model and sampling args:

# Choose model name
model_name = "stabilityai/stablelm-tuned-alpha-7b" #@param ["stabilityai/stablelm-tuned-alpha-7b", "stabilityai/stablelm-base-alpha-7b", "stabilityai/stablelm-tuned-alpha-3b", "stabilityai/stablelm-base-alpha-3b"]

# Select "big model inference" parameters
torch_dtype = "bfloat16" #@param ["float16", "bfloat16", "float"]
load_in_8bit = False #@param {type:"boolean"}
device_map = "auto"
# Sampling args
max_new_tokens = 128 #@param {type:"slider", min:32.0, max:3072.0, step:32}
temperature = 0.7 #@param {type:"slider", min:0.0, max:1.25, step:0.05}
top_k = 0 #@param {type:"slider", min:0.0, max:1.0, step:0.05}
top_p = 0.9 #@param {type:"slider", min:0.0, max:1.0, step:0.05}
do_sample = True #@param {type:"boolean"}

Took 8m 39s to generate via the default prompt for pirate poem on my M2 Max / 38 core GPU

from stablelm.

seanmc9 avatar seanmc9 commented on August 30, 2024 1

Thank you so much for figuring this out and sharing - really helped a lot!!

from stablelm.

tea-lover-418 avatar tea-lover-418 commented on August 30, 2024

Finally got it running, thanks!

However, the default prompt took me over 30 min on the regular M2 Pro, after which I terminated the process.

From what I can see in my activity monitor it's not using the GPU at all, which must be why it's so slow. I'll post it here if I find a solution.

from stablelm.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.