 cebtenzzre
|
48edda30ee
convert : update Falcon script for new HF config (#3448)
|
2 jaren geleden |
 Kenvix ⭐
|
45eba9369f
build : use std::make_tuple() for compatibility with older GCC versions (#3488)
|
2 jaren geleden |
 staviq
|
acec9eaaa9
common : process escape sequences in reverse prompts (#3461)
|
2 jaren geleden |
 shibe2
|
e2583cbc29
CLBlast: Fix handling of on-device tensor data
|
2 jaren geleden |
 Jhen-Jie Hong
|
e8b8d32e86
server : fix incorrect num_tokens_predicted (#3480)
|
2 jaren geleden |
|
Jhen-Jie Hong
|
8f3a642ec1
swift : disable ACCELERATE_NEW_LAPACK (#3481)
|
2 jaren geleden |
|
Jhen-Jie Hong
|
0745384449
ci : add swift build via xcodebuild (#3482)
|
2 jaren geleden |
 Kerfuffle
|
019ba1dcd0
convert : fix Baichuan2 models by using vocab size in config.json (#3299)
|
2 jaren geleden |
 Georgi Gerganov
|
beabc8cfb0
readme : add project status link
|
2 jaren geleden |
|
Georgi Gerganov
|
0d152b37fe
ggml : fix build after #3329
|
2 jaren geleden |
 ds5t5
|
f8c90cdbaa
llm : add Refact model (#3329)
|
2 jaren geleden |
|
Georgi Gerganov
|
f93af02488
sync : ggml (conv 1d + 2d updates, UB fixes) (#3468)
|
2 jaren geleden |
 Merrick Christensen
|
f72f8f22c9
finetune : readme fix typo (#3465)
|
2 jaren geleden |
 Tameem
|
79f34abddb
ggml : add RISC-V Vector Support for K-Quants and improved the existing intrinsics (#3453)
|
2 jaren geleden |
 h-h-h-h
|
8186242b6d
main : consistent prefix/suffix coloring (#3425)
|
2 jaren geleden |
|
Georgi Gerganov
|
ac2219fef3
llama : fix session saving/loading (#3400)
|
2 jaren geleden |
 Alex Klinkhamer
|
48be797ffb
llama : expose model's rope_freq_scale in the API (#3418)
|
2 jaren geleden |
 Jiahao Li
|
f56e1baec3
metal : alibi for arbitrary number of heads (#3426)
|
2 jaren geleden |
 Eve
|
017efe899d
cmake : make LLAMA_NATIVE flag actually use the instructions supported by the processor (#3273)
|
2 jaren geleden |
 goerch
|
ff5a3f0c09
Work on the BPE tokenizer (#3252)
|
2 jaren geleden |
|
cebtenzzre
|
1c84003c08
convert : fix vocab size when not defined in hparams (#3421)
|
2 jaren geleden |
|
cebtenzzre
|
e78f0b0d05
cmake : increase minimum version for add_link_options (#3444)
|
2 jaren geleden |
|
shibe2
|
665018c749
CLBlast: Add broadcast support for matrix multiplication (#3402)
|
2 jaren geleden |
|
cebtenzzre
|
29a404a951
gguf : add BERT, MPT, and GPT-J arch info (#3408)
|
2 jaren geleden |
|
cebtenzzre
|
0fe321031a
gguf : general usability improvements (#3409)
|
2 jaren geleden |
|
cebtenzzre
|
9476b01226
cmake : make CUDA flags more similar to the Makefile (#3420)
|
2 jaren geleden |
 xaedes
|
a03ce38455
finetune : fix #3404 (#3437)
|
2 jaren geleden |
 Adrian
|
a847676984
metal : set log callback before initializing (#3427)
|
2 jaren geleden |
 bandoti
|
095231dfd3
cmake : fix transient definitions in find pkg (#3411)
|
2 jaren geleden |
 Kevin Ji
|
ea55295a74
docker : ignore Git files (#3314)
|
2 jaren geleden |
