 Ben Siraphob
|
bd4b46d6ba
Nix flake: set meta.mainProgram to llama
|
2 years ago |
 Qingyou Meng
|
6b6d5b5024
Fixed tokenizer.model not found error when model dir is symlink (#325)
|
2 years ago |
 Mack Straight
|
a791a68b61
move file magic/version to header, print expected version (#319)
|
2 years ago |
 Bernat Vadell
|
0f1b21cb90
Docker - Fix publish docker image in GitHub Registry (#235)
|
2 years ago |
|
Mack Straight
|
074bea2eb1
sentencepiece bpe compatible tokenizer (#252)
|
2 years ago |
 Stephan Walter
|
5cb63e2493
Add tqdm to Python requirements (#293)
|
2 years ago |
 cocktailpeanut
|
da5303c1ea
bugfix: default should not be interactive (#304)
|
2 years ago |
 Georgi Gerganov
|
4545539d71
Rename script
|
2 years ago |
|
Georgi Gerganov
|
edeba28366
Add temporary helper script for Alpaca chat
|
2 years ago |
 Rickey Bowers Jr
|
5c19c70ba6
fix coloring of last `n_batch` of prompt, and refactor line input (#221)
|
2 years ago |
 tjohnman
|
24568371ae
Support for multiple reverse prompts. (#299)
|
2 years ago |
 Suaj Carrot
|
7392f1cd2c
Improved quantize script (#222)
|
2 years ago |
|
tjohnman
|
ad5fd5b60c
Make prompt randomization optional. (#300)
|
2 years ago |
|
tjohnman
|
368d0c8a9e
Respect the maximum number of tokens in interactive. (#298)
|
2 years ago |
 slaren
|
50fae10d03
Add --ignore-eos parameter (#181)
|
2 years ago |
|
Qingyou Meng
|
084e2f0ec0
interactive mode: print '\n' in sigint_handler, this flush stdout thus ensure color reset. (#283)
|
2 years ago |
 Erik Scholz
|
0b366e7357
Command line switch to use F16 for memory_k and memory_v (refactor of #154) (#294)
|
2 years ago |
|
Georgi Gerganov
|
160bfb217d
Update hot topics to mention Alpaca support
|
2 years ago |
|
Georgi Gerganov
|
c494ed5b94
Fix off-by-one bug (#115)
|
2 years ago |
|
Georgi Gerganov
|
c1c7026b47
Fix python stuff (#109)
|
2 years ago |
 qunash
|
467b149761
Refactoring `convert-pth-to-ggml.py`: more concise and readable (#109)
|
2 years ago |
|
Georgi Gerganov
|
70f01cb863
Drop trailing new line from file prompts (#80)
|
2 years ago |
|
Georgi Gerganov
|
a4e63b73df
Add instruction for using Alpaca (#240)
|
2 years ago |
|
Georgi Gerganov
|
9e1707218a
Add "--instruct" argument for usage with Alpaca (#240)
|
2 years ago |
|
Georgi Gerganov
|
22213a17b5
Change RMSNorm eps to 1e-6 (#173)
|
2 years ago |
 Ronsor
|
d7def1a752
Warn user if a context size greater than 2048 tokens is specified (#274)
|
2 years ago |
 Pavol Rusnak
|
6f61c18ec9
Fix typo in readme
|
2 years ago |
|
Pavol Rusnak
|
1e5a6d088d
Add note about Python 3.11 to readme
|
2 years ago |
|
Pavol Rusnak
|
554b541521
Add memory/disk requirements to readme
|
2 years ago |
 Alex Nguyen
|
d3f202d57b
Remove unused code since n_vocab is model.hparams.n_vocab (#262)
|
2 years ago |
