 Herman Semenov
|
4cb0727698
llava : removed excess free(NULL) operation (#5531)
|
1 year ago |
|
Herman Semenov
|
65085c713e
llama : minor fixed return int value (#5529)
|
1 year ago |
 Alexey Parfenov
|
6dcc02d244
server : add "samplers" param to control the samplers order (#5494)
|
1 year ago |
 Rőczey Barnabás
|
5f5808ca7b
server : fix system prompt cli (#5516)
|
1 year ago |
 bmwl
|
f486f6e1e5
ggml : add numa options (#5377)
|
1 year ago |
 Daniel Bevenius
|
60ed04cf82
llava : fix clip-model-is-vision flag in README.md (#5509)
|
1 year ago |
 Georgi Gerganov
|
594845aab1
ci : fix BERT model download and convert
|
1 year ago |
 Douglas Hanley
|
4524290e87
Use correct type of pooling for embedding models (#5500)
|
1 year ago |
|
Georgi Gerganov
|
c06e45d729
clip : fix wrong loop condition
|
1 year ago |
 slaren
|
9060a1e9df
cuda : print message when initialization fails (#5512)
|
1 year ago |
|
Georgi Gerganov
|
9350a1cf21
scripts : add hf.sh helper script (#5501)
|
1 year ago |
 Michaël de Vries
|
73122473ff
fix(gguf-py): special tokens are no longer skipped when add_<token>_token is set to false (#5487)
|
1 year ago |
 Elbios
|
0d4177126b
llava : fix memory management bug (#5491)
|
1 year ago |
 John
|
7930a8a6e8
llaba : hotfix for llava-1.6 image number (#5495)
|
1 year ago |
 Neuman Vong
|
704359e299
vulkan: Find optimal memory type but with fallback (#5381)
|
1 year ago |
 Rune
|
594fca3fef
readme : fix typo (#5490)
|
1 year ago |
|
John
|
ccbb277f46
llava : update README.md (#5489)
|
1 year ago |
 Michael Podvitskiy
|
8084d55440
cmake : ARM intrinsics detection for MSVC (#5401)
|
1 year ago |
|
John
|
aa23412989
llava : support v1.6 (#5267)
|
1 year ago |
 AT
|
f5ca054855
Early return for zero size calls to get_tensor. (#5482)
|
1 year ago |
|
John
|
6c00a06692
gguf : add python reader example (#5216)
|
1 year ago |
 Jared Van Bortel
|
ea9c8e1143
llama : add support for Nomic Embed (#5468)
|
1 year ago |
 Aarni Koskela
|
c4e6dd59e4
llama : allow raw byte in SPM vocabs; don't crash on nl 404 (#5478)
|
1 year ago |
|
Aarni Koskela
|
037259be68
llama : make load error reporting more granular (#5477)
|
1 year ago |
|
Daniel Bevenius
|
263978904c
finetune : rename feed-forward tensors (w1/w2/w3) (#4839)
|
1 year ago |
|
Georgi Gerganov
|
cf45252a7c
tests : multi-thread the tokenizer tests (#5474)
|
1 year ago |
|
Douglas Hanley
|
03bf161eb6
llama : support batched embeddings (#5466)
|
1 year ago |
 Johannes Gäßler
|
ad014bba97
make: add error message for bad CUDA version (#5444)
|
1 year ago |
|
Georgi Gerganov
|
49cc1f7d67
bert : add tests + fix quantization (#5475)
|
1 year ago |
|
Georgi Gerganov
|
99b8b43d7b
tests : disable moe test (#5473)
|
1 year ago |
