 Georgi Gerganov
|
db3abcc114
sync : ggml (ggml-backend) (#3548)
|
2 anos atrás |
 Matheus C. França
|
eee42c670e
ci : add Zig CI/CD and fix build (#2996)
|
2 anos atrás |
 Ryder Wishart
|
8e6716a102
api_like_OAI.py : compat with Microsoft Guidance (#2746)
|
2 anos atrás |
 arcrank
|
9c38d181d4
api_like_OAI.py : simplify function (#2796)
|
2 anos atrás |
 Johannes Rudolph
|
a1202a31ed
k-quants : fix comments about block sizing (#3499)
|
2 anos atrás |
|
Georgi Gerganov
|
94e502dfb7
ci : enable on obj-c changes + fix metal build (#3540)
|
2 anos atrás |
 Luo Tian
|
7d8b24932f
zig : fix build by introducing train.cpp (#3539)
|
2 anos atrás |
|
Georgi Gerganov
|
b0ec5218c3
metal : support MTLGPUFamily < Apple7, formatting, style (#3524)
|
2 anos atrás |
 Kerfuffle
|
63d3b06a43
llama : fix missing break in Persimmon arch case statements (#3535)
|
2 anos atrás |
|
Kerfuffle
|
a16e89cec8
Fix trying to strip newline from empty prompt and cfg prompt file content (#3534)
|
2 anos atrás |
 M. Yusuf Sarıgöz
|
4d03833211
gguf.py : fix CI for publishing GGUF package (#3532)
|
2 anos atrás |
 Tom C
|
c47066d833
py : change version of numpy requirement to 1.24.4 (#3515)
|
2 anos atrás |
 cebtenzzre
|
f1782c68de
quantize : fail fast on write errors (#3521)
|
2 anos atrás |
 Jhen-Jie Hong
|
c26765a0a1
metal : support default.metallib load & reuse code for swift package (#3522)
|
2 anos atrás |
 Phillip Kravtsov
|
0e797c2fc5
llm : support Adept Persimmon 8B (#3410)
|
2 anos atrás |
 goerch
|
3a716b4dae
Fix for #3454 (#3455)
|
2 anos atrás |
 BarfingLemurs
|
1faaae8c2b
readme : update models, cuda + ppl instructions (#3510)
|
2 anos atrás |
 Mihai
|
cb13d73a72
server : docs fix default values and add n_probs (#3506)
|
2 anos atrás |
|
Kerfuffle
|
9ca79d5cbb
kv cache slot search improvements (#3493)
|
2 anos atrás |
|
Georgi Gerganov
|
0c731ca403
prompts : fix editorconfig checks after #3416
|
2 anos atrás |
 pudepiedj
|
a8777ad84e
parallel : add option to load external prompt file (#3416)
|
2 anos atrás |
|
Jhen-Jie Hong
|
97af49fa39
server : reuse llama_sample_token common util (#3494)
|
2 anos atrás |
 l3utterfly
|
16820a5a0d
llama : correct hparams comparison (#3446)
|
2 anos atrás |
|
Jhen-Jie Hong
|
04b2f4386e
ci : fix xcodebuild destinations (#3491)
|
2 anos atrás |
|
cebtenzzre
|
48edda30ee
convert : update Falcon script for new HF config (#3448)
|
2 anos atrás |
 Kenvix ⭐
|
45eba9369f
build : use std::make_tuple() for compatibility with older GCC versions (#3488)
|
2 anos atrás |
 staviq
|
acec9eaaa9
common : process escape sequences in reverse prompts (#3461)
|
2 anos atrás |
 shibe2
|
e2583cbc29
CLBlast: Fix handling of on-device tensor data
|
2 anos atrás |
|
Jhen-Jie Hong
|
e8b8d32e86
server : fix incorrect num_tokens_predicted (#3480)
|
2 anos atrás |
|
Jhen-Jie Hong
|
8f3a642ec1
swift : disable ACCELERATE_NEW_LAPACK (#3481)
|
2 anos atrás |
