| # So you want to run GPT-J-6B using HuggingFace+FastAPI on a local rig (3090 or TITAN) ... tricky. | |
| # special help from the Kolob Colab server https://colab.research.google.com/drive/1VFh5DOkCJjWIrQ6eB82lxGKKPgXmsO5D?usp=sharing#scrollTo=iCHgJvfL4alW | |
| # Conversion to HF format (12.6GB tar image) found at https://drive.google.com/u/0/uc?id=1NXP75l1Xa5s9K18yf3qLoZcR6p4Wced1&export=download | |
| # Uses GDOWN to get the image | |
| # You will need 26 GB of space, 12+GB for the tar and 12+GB expanded (you can nuke the tar after expansion) | |
| # Near Simplest Language model API, with room to expand! | |
| # runs GPT-J-6B on 3090 and TITAN and servers it using FastAPI | |
| # change "seq" (which is the context size) to adjust footprint |
| # Near Simplest Language model API, with room to expand! | |
| # runs GPT-J-6B on 3090 and TITAN and servers it using FastAPI | |
| # change "seq" (which is the context size) to adjust footprint | |
| # | |
| # seq vram usage | |
| # 512 14.7G | |
| # 900 15.3G | |
| # uses FastAPI, so install that | |
| # https://fastapi.tiangolo.com/tutorial/ |
Microsoft Visual Studio Code freezes can be extremely frustrating. I experienced it and spent hours looking for solutions.
The result is this comprehensive list of every solution I found to solve the freezing VSCode problem!
There can be multiple origins to the freeze, so I suggest that you try multiple of these solutions until the problem disappears.
Each worked for at least 1 person, and there is a link to the source for each. Hoping that it will solve your problem!
Markdown is a way to quickly & simply style text for the web by using .md files.
GitHub Flavored Markdown add new functionnalities on top of regular markdown to let you create beautiful & interactive documents in GitHub and GitHub Enterprise.
This gist covers all the main & advanced options you have with markdown & github markdown.
This file itself is created with github markdown, click the "Raw" button to see its contents !