 Phillip Kravtsov
|
0e797c2fc5
llm : support Adept Persimmon 8B (#3410)
|
2 years ago |
 goerch
|
3a716b4dae
Fix for #3454 (#3455)
|
2 years ago |
 BarfingLemurs
|
1faaae8c2b
readme : update models, cuda + ppl instructions (#3510)
|
2 years ago |
 Mihai
|
cb13d73a72
server : docs fix default values and add n_probs (#3506)
|
2 years ago |
 Kerfuffle
|
9ca79d5cbb
kv cache slot search improvements (#3493)
|
2 years ago |
 Georgi Gerganov
|
0c731ca403
prompts : fix editorconfig checks after #3416
|
2 years ago |
 pudepiedj
|
a8777ad84e
parallel : add option to load external prompt file (#3416)
|
2 years ago |
 Jhen-Jie Hong
|
97af49fa39
server : reuse llama_sample_token common util (#3494)
|
2 years ago |
 l3utterfly
|
16820a5a0d
llama : correct hparams comparison (#3446)
|
2 years ago |
|
Jhen-Jie Hong
|
04b2f4386e
ci : fix xcodebuild destinations (#3491)
|
2 years ago |
 cebtenzzre
|
48edda30ee
convert : update Falcon script for new HF config (#3448)
|
2 years ago |
 Kenvix ⭐
|
45eba9369f
build : use std::make_tuple() for compatibility with older GCC versions (#3488)
|
2 years ago |
 staviq
|
acec9eaaa9
common : process escape sequences in reverse prompts (#3461)
|
2 years ago |
 shibe2
|
e2583cbc29
CLBlast: Fix handling of on-device tensor data
|
2 years ago |
|
Jhen-Jie Hong
|
e8b8d32e86
server : fix incorrect num_tokens_predicted (#3480)
|
2 years ago |
|
Jhen-Jie Hong
|
8f3a642ec1
swift : disable ACCELERATE_NEW_LAPACK (#3481)
|
2 years ago |
|
Jhen-Jie Hong
|
0745384449
ci : add swift build via xcodebuild (#3482)
|
2 years ago |
|
Kerfuffle
|
019ba1dcd0
convert : fix Baichuan2 models by using vocab size in config.json (#3299)
|
2 years ago |
|
Georgi Gerganov
|
beabc8cfb0
readme : add project status link
|
2 years ago |
|
Georgi Gerganov
|
0d152b37fe
ggml : fix build after #3329
|
2 years ago |
 ds5t5
|
f8c90cdbaa
llm : add Refact model (#3329)
|
2 years ago |
|
Georgi Gerganov
|
f93af02488
sync : ggml (conv 1d + 2d updates, UB fixes) (#3468)
|
2 years ago |
 Merrick Christensen
|
f72f8f22c9
finetune : readme fix typo (#3465)
|
2 years ago |
 Tameem
|
79f34abddb
ggml : add RISC-V Vector Support for K-Quants and improved the existing intrinsics (#3453)
|
2 years ago |
 h-h-h-h
|
8186242b6d
main : consistent prefix/suffix coloring (#3425)
|
2 years ago |
|
Georgi Gerganov
|
ac2219fef3
llama : fix session saving/loading (#3400)
|
2 years ago |
 Alex Klinkhamer
|
48be797ffb
llama : expose model's rope_freq_scale in the API (#3418)
|
2 years ago |
 Jiahao Li
|
f56e1baec3
metal : alibi for arbitrary number of heads (#3426)
|
2 years ago |
 Eve
|
017efe899d
cmake : make LLAMA_NATIVE flag actually use the instructions supported by the processor (#3273)
|
2 years ago |
|
goerch
|
ff5a3f0c09
Work on the BPE tokenizer (#3252)
|
2 years ago |
