 Diego Devesa
|
7eee341bee
common : use common_ prefix for common library functions (#9805)
|
1 anno fa |
 Georgi Gerganov
|
f4d2b8846a
llama : add reranking support (#9510)
|
1 anno fa |
|
Georgi Gerganov
|
6262d13e0b
common : reimplement logging (#9418)
|
1 anno fa |
|
Georgi Gerganov
|
0abc6a2c25
llama : llama_perf + option to disable timings during decode (#9355)
|
1 anno fa |
|
slaren
|
49006c67b4
llama : move random seed generation to the samplers (#9398)
|
1 anno fa |
 Xuan Son Nguyen
|
bfe76d4a17
common : move arg parser code to `arg.cpp` (#9388)
|
1 anno fa |
|
Xuan Son Nguyen
|
1b9ae5189c
common : refactor arg parser (#9308)
|
1 anno fa |
|
Georgi Gerganov
|
df270ef745
llama : refactor sampling v2 (#9294)
|
1 anno fa |
 fairydreaming
|
7c3f55c100
Add support for encoder-only T5 models (#8900)
|
1 anno fa |
 Liu Jia
|
0a4ce78681
common : Changed tuple to struct (TODO fix) (#8823)
|
1 anno fa |
 Yann Follet
|
646ef4a9cf
embedding : more cli arguments (#7458)
|
1 anno fa |
 Douglas Hanley
|
80ea089d77
llama : allow pooled embeddings on any model (#7477)
|
1 anno fa |
|
Georgi Gerganov
|
1442677f92
common : refactor cli arg parsing (#7675)
|
1 anno fa |
|
Georgi Gerganov
|
6ff13987ad
common : normalize naming style (#7462)
|
1 anno fa |
 dm4
|
ea3b0590ee
embedding : free the batch after execution (#7297)
|
1 anno fa |
 Joan Fontanals
|
b83cc3f5b3
llama : add Jina Embeddings architecture (#6826)
|
1 anno fa |
 Jared Van Bortel
|
1b67731e18
BERT tokenizer fixes (#6498)
|
1 anno fa |
 howlger
|
1e13987fba
embedding : show full embedding for single prompt (#6342)
|
1 anno fa |
 Minsoo Cheong
|
deb7240100
embedding : adjust `n_ubatch` value (#6296)
|
1 anno fa |
|
Georgi Gerganov
|
044ec4b2a5
embedding : add EOS token if not present (#899)
|
1 anno fa |
|
Georgi Gerganov
|
68265ebfc6
embedding : print all resulting embeddings (#899)
|
1 anno fa |
|
Georgi Gerganov
|
0fd6c1f015
embedding : print cosine similarity (#899)
|
1 anno fa |
|
slaren
|
f30ea47a87
llama : add pipeline parallelism support (#6017)
|
1 anno fa |
 SeungWon Jeong
|
fb215c3832
server : normalize embeddings (#5956)
|
1 anno fa |
|
Georgi Gerganov
|
29ae62d2ae
llama : fix embeddings (#5796)
|
1 anno fa |
 bmwl
|
f486f6e1e5
ggml : add numa options (#5377)
|
1 anno fa |
|
Douglas Hanley
|
03bf161eb6
llama : support batched embeddings (#5466)
|
1 anno fa |
|
Douglas Hanley
|
2891c8aa9a
Add support for BERT embedding models (#5423)
|
1 anno fa |
 cebtenzzre
|
b12fa0d1c1
build : link against build info instead of compiling against it (#3879)
|
2 anni fa |
|
slaren
|
16bc66d947
llama.cpp : split llama_context_params into model and context params (#3301)
|
2 anni fa |
