cosmopolitan

mirror of https://github.com/jart/cosmopolitan.git synced 2025-03-03 07:29:23 +00:00

History

Justine Tunney 1c2da3a55a Make shell usability improvements to llama.cpp - Introduce -v and --verbose flags - Don't print stats / diagnostics unless -v is passed - Reduce --top_p default from 0.95 to 0.70 - Change --reverse-prompt to no longer imply --interactive - Permit --reverse-prompt specifying custom EOS if non-interactive		2023-04-28 02:54:11 -07:00
..
common.cc	Make shell usability improvements to llama.cpp	2023-04-28 02:54:11 -07:00
common.h	Make shell usability improvements to llama.cpp	2023-04-28 02:54:11 -07:00
ggml.c	Further optimize the math library	2023-04-28 01:20:47 -07:00
ggml.h	Import llama.cpp	2023-04-27 14:37:14 -07:00
ggml.mk	Import llama.cpp	2023-04-27 14:37:14 -07:00
LICENSE	Import llama.cpp	2023-04-27 14:37:14 -07:00
llama.cc	Make shell usability improvements to llama.cpp	2023-04-28 02:54:11 -07:00
llama.h	Make shell usability improvements to llama.cpp	2023-04-28 02:54:11 -07:00
llama_util.h	Import llama.cpp	2023-04-27 14:37:14 -07:00
main.cc	Make shell usability improvements to llama.cpp	2023-04-28 02:54:11 -07:00
README.cosmo	Make shell usability improvements to llama.cpp	2023-04-28 02:54:11 -07:00

README.cosmo

DESCRIPTION

  ggml is a machine learning library useful for LLM inference on CPUs

LICENSE

  MIT

ORIGIN

  https://github.com/ggerganov/llama.cpp
  commit 0b2da20538d01926b77ea237dd1c930c4d20b686
  Author: Stephan Walter <stephan@walter.name>
  Date:   Wed Apr 26 20:26:42 2023 +0000
  ggml : slightly faster AVX2 implementation for Q5 (#1197)

LOCAL CHANGES

  - Introduce -v and --verbose flags
  - Don't print stats / diagnostics unless -v is passed
  - Reduce --top_p default from 0.95 to 0.70
  - Change --reverse-prompt to no longer imply --interactive
  - Permit --reverse-prompt specifying custom EOS if non-interactive
  - Refactor headers per cosmo convention
  - Replace code like 'ggjt' with READ32BE("ggjt")
  - Remove C++ exceptions; use Die() function instead