e81b9c81c1
Update Contributing section
1 year ago
367946c668
Don't tell users to use a bad number of threads ( #243 )
...
The readme tells people to use the command line option "-t 8", causing 8
threads to be started. On systems with fewer than 8 cores, this causes a
significant slowdown. Remove the option from the example command lines
and use /proc/cpuinfo on Linux to determine a sensible default.
1 year ago
2af23d3043
🚀 Dockerize llamacpp ( #132 )
...
* feat: dockerize llamacpp
* feat: split build & runtime stages
* split dockerfile into main & tools
* add quantize into tool docker image
* Update .devops/tools.sh
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* add docker action pipeline
* change CI to publish at github docker registry
* fix name runs-on macOS-latest is macos-latest (lowercase)
* include docker versioned images
* fix github action docker
* fix docker.yml
* feat: include all-in-one command tool & update readme.md
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
1 year ago
721311070e
Update README.md
1 year ago
ac15de7895
Expand "Contributing" section
1 year ago
273abc47ff
Update hot topics - RMSnorm
1 year ago
27944c4206
fixed typo ( #178 )
1 year ago
977295c700
Fix potential licensing issue ( #126 )
...
* Update README.md
* Update README.md
remove facebook
1 year ago
60f819a2b1
Add section to README on how to run the project on Android ( #130 )
1 year ago
97ab2b2578
Add Misc section + update hot topics + minor fixes
1 year ago
7ec903d3c1
Update contribution section, hot topics, limitations, etc.
1 year ago
d1f224712d
Add quantize script for batch quantization ( #92 )
...
* Add quantize script for batch quantization
* Indentation
* README for new quantize.sh
* Fix script name
* Fix file list on Mac OS
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
1 year ago
1808ee0500
Add initial contribution guidelines
1 year ago
1a0a74300f
Update README.md
1 year ago
96ea727f47
Add interactive mode ( #61 )
...
* Initial work on interactive mode.
* Improve interactive mode. Make rev. prompt optional.
* Update README to explain interactive mode.
* Fix OS X build
1 year ago
9661954835
Fix typo in README ( #45 )
1 year ago
7027a97837
Update README.md
1 year ago
7c9e54e55e
Revert "weights_only" arg - this causing more trouble than help
1 year ago
b9bd1d0141
python/pytorch compat notes ( #44 )
1 year ago
702fddf5c5
Clarify meaning of hacking
1 year ago
7d86e25bf6
README: add "Supported platforms" + update hot topics
1 year ago
da1a4ff01f
Update README.md
1 year ago
6b2cb6302f
Fix a typo in model name ( #16 )
1 year ago
4235e3d5b3
Update README.md
1 year ago
f1eaff4721
Add AVX2 support for x86 architectures thanks to @Const-me !
1 year ago
0c6803321c
Update README.md
1 year ago
7211862c94
Update Makefile var + add comment
1 year ago
a5c5ae2f54
Update README.md
1 year ago
ea977e85ec
Update README.md
1 year ago
007a8f6f45
Support all LLaMA models + change Q4_0 quantization storage
1 year ago
5f2f970d51
Include Python dependencies in README ( #6 )
1 year ago
73c6ed5e87
Update README.md
1 year ago
01eeed8fb1
Update README.md
1 year ago
6da2df34ee
Update README.md
1 year ago
920a7fe2d9
Update README.md
1 year ago
3a57ee59de
Update README.md
1 year ago
b85028522d
Update README.md
1 year ago
8a01f565ff
Update README.md
1 year ago
18ebda34d6
Update README.md
1 year ago
319cdb3e1f
Final touches
1 year ago
775328064e
Create README.md
1 year ago
Georgi Gerganov
Stephan Walter
Bernat Vadell
moritzbrantner
Musab Gultekin
Radoslav Gerganov
Pavol Rusnak
Matvey Soloviev
Marc Köhlbrugge
Oleksandr Nikitin
Juraj Bednar
Simon Willison