 M. Yusuf Sarıgöz
|
8194cd8772
gguf : export objects to user code (#2780)
|
il y a 2 ans |
 Henri Vasserman
|
6bbc598a63
ROCm Port (#1087)
|
il y a 2 ans |
 Georgi Gerganov
|
3f460a2b72
cuda : add RoPE kernel for mode == 2 (NeoX) (#2760)
|
il y a 2 ans |
|
M. Yusuf Sarıgöz
|
87e3733f24
gguf : make gguf pip-installable
|
il y a 2 ans |
 Shouzheng Liu
|
b91ad7f461
ggml-alloc : enlarge size of parse_seq (#2776)
|
il y a 2 ans |
 Marcus Dunn
|
2e5f70a25f
Added `enum` to `llama_token_get_type` return type (#2774)
|
il y a 2 ans |
 slaren
|
d0f77b1353
convert.py : try to determine n_ctx automatically for CodeLlama (#2770)
|
il y a 2 ans |
|
slaren
|
0d3094f0c7
gguf : add rope_freq_base parameter for CodeLlama (#2769)
|
il y a 2 ans |
|
Georgi Gerganov
|
01f2224682
falcon : write file type
|
il y a 2 ans |
|
Shouzheng Liu
|
38b16dfca6
metal : bug-fix when enable ggml-alloc (#2757)
|
il y a 2 ans |
|
Georgi Gerganov
|
8f8c28e89c
convert : auto-determine model name based on dir + scripts update
|
il y a 2 ans |
 Kerfuffle
|
7694adda8d
Fix for main example getting stuck when -n -2 and --interactive (#2767)
|
il y a 2 ans |
|
slaren
|
fea95c682d
fix convert.py for codellama, add llama 34B to the list of recognized models (#2768)
|
il y a 2 ans |
 DannyDaemonic
|
ef955fbd23
Tag release with build number (#2732)
|
il y a 2 ans |
|
Georgi Gerganov
|
d67777c202
metal : add Q8_0 support (#2763)
|
il y a 2 ans |
|
Georgi Gerganov
|
c3e53b421a
llama : escape all U+2581 in a string (#2750)
|
il y a 2 ans |
 Evan Jones
|
6e91a1b070
llama : fix grammar sometimes generating null char (#2756)
|
il y a 2 ans |
|
Georgi Gerganov
|
44d5462b5c
readme : fix link
|
il y a 2 ans |
|
Georgi Gerganov
|
c7868b0753
minor : fix trailing whitespace
|
il y a 2 ans |
|
Georgi Gerganov
|
79da24b58c
readme : update hot topics
|
il y a 2 ans |
|
Georgi Gerganov
|
cf658adc83
llm : add Falcon support (#2717)
|
il y a 2 ans |
|
Georgi Gerganov
|
a192860cfe
minor : fix trailing whitespace
|
il y a 2 ans |
 Olivier Chafik
|
95385241a9
examples : restore the functionality to import llama2.c models (#2685)
|
il y a 2 ans |
|
slaren
|
335acd2ffd
fix convert-lora-to-ggml.py (#2738)
|
il y a 2 ans |
 klosax
|
5290c38e6e
main : insert bos if no tokens (#2727)
|
il y a 2 ans |
 akawrykow
|
cc34dbda96
gitignore : fix for windows (#2729)
|
il y a 2 ans |
 Cebtenzzre
|
7c2227a197
chmod : make scripts executable (#2675)
|
il y a 2 ans |
 JohnnyB
|
f19dca04ea
devops : RPM Specs (#2723)
|
il y a 2 ans |
 Kawrakow
|
8207214b6a
Fix values shown in the quantize tool help (#2735)
|
il y a 2 ans |
|
Kawrakow
|
62959e740e
Strided perplexity (#2714)
|
il y a 2 ans |
