 Georgi Gerganov
|
9588f196b1
train : change default FA argument (#7528)
|
1 year ago |
|
Georgi Gerganov
|
6ff13987ad
common : normalize naming style (#7462)
|
1 year ago |
|
Georgi Gerganov
|
ab336a9d5e
code : normalize enum names (#5697)
|
1 year ago |
|
Georgi Gerganov
|
5cb04dbc16
llama : remove LLAMA_MAX_DEVICES and LLAMA_SUPPORTS_GPU_OFFLOAD (#5240)
|
1 year ago |
 Daniel Bevenius
|
cb1e2818e0
train : fix typo in overlapping-samples help msg (#4758)
|
2 years ago |
 slaren
|
cafcd4f895
ggml : remove n_dims from ggml_tensor (#4469)
|
2 years ago |
 Jiří Podivín
|
ba4cf5c0bf
train : move number of gpu layers argument parsing to common/train.cpp (#4074)
|
2 years ago |
|
Georgi Gerganov
|
4760e7cc0b
sync : ggml (backend v2) (#3912)
|
2 years ago |
 Andrew Godfrey
|
73bdcb395e
finetune : add -ngl parameter (#3762)
|
2 years ago |
 Marcus Dunn
|
5be6c803fa
llama : remove token functions with `context` args in favor of `model` (#3720)
|
2 years ago |
 Herman Semenov
|
f439e506e8
ggml : fix rope + llama minor optimizations (#3560)
|
2 years ago |
 staviq
|
1a159553f9
tokenizer : special token handling (#3538)
|
2 years ago |
|
slaren
|
16bc66d947
llama.cpp : split llama_context_params into model and context params (#3301)
|
2 years ago |
 xaedes
|
0e76a8992c
train : finetune LORA (#2632)
|
2 years ago |
