 Kerfuffle
|
dc07dc492e
convert : various script cleanups/fixes + merges and special token handling (#2842)
|
2 years ago |
 chaihahaha
|
ad9ddcff6e
llm.vim : stop generation at multiple linebreaks, bind to <F2> (#2879)
|
2 years ago |
 staviq
|
8341a25957
main : log file (#2748)
|
2 years ago |
 Cebtenzzre
|
849408957c
tests : add a C compliance test (#2848)
|
2 years ago |
 slaren
|
06abf8eeba
ggml : add view_src and view_offs to ggml_tensor for views (#2874)
|
2 years ago |
|
slaren
|
c03a243abf
remove outdated references to -eps and -gqa from README (#2881)
|
2 years ago |
 Kawrakow
|
fa3582f509
Tell users attmepting to run perplexity with too few tokens to use more (#2882)
|
2 years ago |
|
Kawrakow
|
e37e69dcc3
10X faster BPE tokenizer (#2876)
|
2 years ago |
 maddes8cht
|
53885d7256
py : fix "usage" messages (#2873)
|
2 years ago |
 jameswu2014
|
bcce96ba4d
convert.py : fix baichuan7B support (#2870)
|
2 years ago |
 Jhen-Jie Hong
|
74e0caeb82
readme : add react-native binding (#2869)
|
2 years ago |
|
Cebtenzzre
|
d4b5e16c32
make : fix clang tests build, add missing examples (#2859)
|
2 years ago |
 Georgi Gerganov
|
3a007648f2
metal : add option to disable debug logs (close #2764)
|
2 years ago |
|
Georgi Gerganov
|
611363ac79
scripts : add pipefail
|
2 years ago |
 Marcus Dunn
|
95b6e5212f
added `struct` to llama_dump_timing_info_yaml's `llama_context` (#2857)
|
2 years ago |
 xaedes
|
44c117f41e
train : mem usage and other improvements (#2439)
|
2 years ago |
|
slaren
|
43033b7bb4
llama-bench : set locale to utf8 (#2832)
|
2 years ago |
 Johannes Gäßler
|
6b73ef1201
YAML result logging + preset script (#2657)
|
2 years ago |
 alonfaraj
|
75fafcbccc
make : fix tests build (#2855)
|
2 years ago |
 grahameth
|
be475f60af
llama.cpp : fix wrong vsnprintf call in MS compiler (#2856)
|
2 years ago |
 Ronny Brendel
|
3af6b86301
ggml : tiny ggml_vec_dot_q4_K_q8_K AVX2 improvement (#2819)
|
2 years ago |
|
Georgi Gerganov
|
35feac6560
ggml : sync (mem align to header + conv_transpose_2d fixes + ggml_alloc) (#2852)
|
2 years ago |
|
Johannes Gäßler
|
92b1bbd2ec
CUDA: fix RoPE asserts, block sizes (#2833)
|
2 years ago |
 igarnier
|
dd0dc366da
llama.h : add missing struct keyword for C compat in callback type (#2847)
|
2 years ago |
|
Georgi Gerganov
|
f55538c3cc
metal : fix memory leak (#2762)
|
2 years ago |
|
Cebtenzzre
|
ebcee207b6
quantize : make output filename optional again (#2823)
|
2 years ago |
 JohnnyB
|
3e8ff47af6
devops : added systemd units and set versioning to use date. (#2835)
|
2 years ago |
|
Georgi Gerganov
|
103cfafc77
gguf : fix strings to not be null-terminated (#2839)
|
2 years ago |
|
Georgi Gerganov
|
c10704d01e
llama : fix MPI threads (close #2827)
|
2 years ago |
 Olivier Chafik
|
230d46c723
examples : update llama2.c converter to read vocab and write models in GGUF format (#2751)
|
2 years ago |
