 Georgi Gerganov
|
d6a04f872d
ggml : hide ggml_object, ggml_cgraph, ggml_hash_set (#9408)
|
пре 1 година |
 Xuan Son Nguyen
|
bfe76d4a17
common : move arg parser code to `arg.cpp` (#9388)
|
пре 1 година |
|
Xuan Son Nguyen
|
1b9ae5189c
common : refactor arg parser (#9308)
|
пре 1 година |
 Faisal Zaghloul
|
42c76d1358
Threadpool: take 2 (#8672)
|
пре 1 година |
|
Xuan Son Nguyen
|
828d6ff7d7
export-lora : throw error if lora is quantized (#9002)
|
пре 1 година |
|
Georgi Gerganov
|
45a55b91aa
llama : better replace_all (cont) (#8926)
|
пре 1 година |
|
Xuan Son Nguyen
|
1e6f6554aa
server : add lora hotswap endpoint (WIP) (#8857)
|
пре 1 година |
|
Xuan Son Nguyen
|
41cd47caab
examples : export-lora : fix issue with quantized base models (#8687)
|
пре 1 година |
|
Xuan Son Nguyen
|
de280085e7
examples : Fix `llama-export-lora` example (#8607)
|
пре 1 година |
 Steve Bonds
|
37b12f92ab
export-lora : handle help argument (#8497)
|
пре 1 година |
 Ananta Bastola
|
6e4e973b26
ci : add an option to fail on compile warning (#3952)
|
пре 1 година |
|
Georgi Gerganov
|
3b169441df
sync : ggml (#5452)
|
пре 1 година |
 Daniel Bevenius
|
930f907d3e
export-lora : use LLAMA_FILE_MAGIC_GGLA (#4894)
|
пре 2 година |
|
Georgi Gerganov
|
afefa319f1
ggml : change ggml_scale to take a float instead of tensor (#4573)
|
пре 2 година |
|
Georgi Gerganov
|
4760e7cc0b
sync : ggml (backend v2) (#3912)
|
пре 2 година |
 xaedes
|
0e76a8992c
train : finetune LORA (#2632)
|
пре 2 година |
