Skip to content

Instantly share code, notes, and snippets.

View Qubitium's full-sized avatar

Qubitium Qubitium

View GitHub Profile
@shawwn
shawwn / 65b_samples.txt
Last active May 18, 2023 06:35
Some LLaMA 65B outputs after fixing the sampler settings.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
{"seed": 374894, "temp": 0.7, "top_p": 0.0, "top_k": 40, "repetition_penalty": 1.1764705882352942, "max_seq_len": 512, "max_gen_len": 511}
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Loading
Loaded in 8.72 seconds
============== sample 1 =================
I believe the meaning of life is to grow, learn and give.
@benob
benob / reshard.py
Created March 4, 2023 17:35
Script to decompose/recompose LLAMA LLM models with different number of shards.
# script to decompose/recompose llama model in different number of shards
# note that it loads the full model * 2 in cpu memory
import os
import json
import sys
import torch
import glob
if len(sys.argv) != 4:
@mislav
mislav / releasenotes.md
Created November 3, 2011 19:10
Zepto.js v0.8 release notes

Changes in Zepto since v0.7

Most notable additions in [Zepto][gh] 0.8 are:

  1. CSS transitions for every browser with animate() method;
  2. Unified event handling with fn.on() & off();
  3. Ajax global events, timeout support, and other improvements;
  4. Performance boost for selectors;
  5. 2 new add-ons.