 Georgi Gerganov
|
b47b8a9cfe
llama : optimize memory buffers (#2325)
|
2 years ago |
 klosax
|
b5fe67f8c6
Perplexity: Compute scores correlated to HellaSwag (#2312)
|
2 years ago |
 whoreson
|
24baa54ac1
examples : basic VIM plugin
|
2 years ago |
|
Georgi Gerganov
|
dd6c67d3cb
ci : fix args
|
2 years ago |
|
Georgi Gerganov
|
5d500e8ccf
ci : add 7B CUDA tests (#2319)
|
2 years ago |
 Richard Roberson
|
7d5f18468c
examples : add easy python script to create quantized (k-bit support) GGML models from local HF Transformer models (#2311)
|
2 years ago |
 Kawrakow
|
d924522a46
Custom RoPE + bettter memory management for CUDA (#2295)
|
2 years ago |
|
Kawrakow
|
4d76a5f49b
Faster Q3_K implementation on Metal (#2307)
|
2 years ago |
|
Georgi Gerganov
|
0db14fef06
ggml : fix the rope fix (513f8619535a64fa9ace808cdcbcf66211535f5c)
|
2 years ago |
 Ikko Eltociear Ashimine
|
03e566977b
examples : fix typo in minigpt4.py (#2298)
|
2 years ago |
|
Georgi Gerganov
|
513f861953
ggml : fix rope args order + assert (#2054)
|
2 years ago |
|
Georgi Gerganov
|
3973b25a64
gitignore : fix final newline
|
2 years ago |
 Guillaume "Vermeille" Sanchez
|
ab0e26bdfb
llama : remove cfg smooth factor as it is only a reparameterization of the guidance scale (#2280)
|
2 years ago |
 Jose Maldonado
|
73643f5fb1
gitignore : changes for Poetry users + chat examples (#2284)
|
2 years ago |
|
Georgi Gerganov
|
a814d04f81
make : fix indentation
|
2 years ago |
|
Georgi Gerganov
|
4c013bb738
ci : fix MNT realpath usage (#2250)
|
2 years ago |
 Sky Yan
|
42c7c2e2e9
make : support customized LLAMA_CUDA_NVCC and LLAMA_CUDA_CCBIN (#2275)
|
2 years ago |
 wzy
|
78a3d13424
flake : remove intel mkl from flake.nix due to missing files (#2277)
|
2 years ago |
|
Georgi Gerganov
|
ae178ab46b
llama : make tensor_split ptr instead of array (#2272)
|
2 years ago |
 Jiří Podivín
|
54e3bc76fe
make : add new target for test binaries (#2244)
|
2 years ago |
 Hatsune Miku
|
019fe257bb
MIKU MAYHEM: Upgrading the Default Model for Maximum Fun 🎉 (#2287)
|
2 years ago |
|
Kawrakow
|
e68c96f7fe
Faster Q2_K on Metal (#2297)
|
2 years ago |
 Przemysław Pawełczyk
|
9cf022a188
make : fix embdinput library and server examples building on MSYS2 (#2235)
|
2 years ago |
|
Kawrakow
|
e782c9e735
Faster Q5_K and Q6_K on Metal (#2294)
|
2 years ago |
|
Kawrakow
|
785829dfe8
Faster Q4_K on Metal (#2290)
|
2 years ago |
|
Georgi Gerganov
|
fff0e0eafe
llama : fix regression from #2000 - could not load no-mmap models
|
2 years ago |
 Shouzheng Liu
|
417a85a001
metal: minor q4 optimization and reduce code size (#2248)
|
2 years ago |
 Rinne
|
294f424554
llama : extend API to get max devices at runtime (#2253)
|
2 years ago |
|
wzy
|
45a1b07e9b
flake : update flake.nix (#2270)
|
2 years ago |
|
wzy
|
b1f4290953
cmake : install targets (#2256)
|
2 years ago |
