 Alexey Parfenov
|
a803333a4e
common : use enums for sampler types (#5418)
|
1 vuosi sitten |
 Jared Van Bortel
|
1ec3332ade
YaRN : store rope scaling type as int32_t in memory (#5285)
|
1 vuosi sitten |
 Georgi Gerganov
|
5cb04dbc16
llama : remove LLAMA_MAX_DEVICES and LLAMA_SUPPORTS_GPU_OFFLOAD (#5240)
|
1 vuosi sitten |
 Kawrakow
|
6f9939d119
KL-divergence (#5076)
|
2 vuotta sitten |
|
Kawrakow
|
7dcbe39d36
Add ability to evauate multiple choice tasks (#5047)
|
2 vuotta sitten |
|
Kawrakow
|
682986a08e
Add Winogrande evaluation (#5015)
|
2 vuotta sitten |
 stduhpf
|
e0324285a5
speculative : threading options (#4959)
|
2 vuotta sitten |
 Yann Follet
|
722d33f34e
main : add parameter --no-display-prompt (#4541)
|
2 vuotta sitten |
 slaren
|
e7e4df031b
llama : ggml-backend integration (#4766)
|
2 vuotta sitten |
|
Georgi Gerganov
|
7edefbd79c
main : better name for variable n_print (#4874)
|
2 vuotta sitten |
|
Georgi Gerganov
|
3ca63b4538
main : disable token count by default (#4874)
|
2 vuotta sitten |
 pudepiedj
|
43f76bf1c3
main : print total token count and tokens consumed so far (#4874)
|
2 vuotta sitten |
|
Georgi Gerganov
|
52531fdff8
main : add self-extend support (#4815)
|
2 vuotta sitten |
 LeonEricsson
|
7082d24cec
lookup : add prompt lookup decoding example (#4484)
|
2 vuotta sitten |
|
Georgi Gerganov
|
bcc0eb4591
llama : per-layer KV cache + quantum K cache (#4309)
|
2 vuotta sitten |
 Kerfuffle
|
5aa365d88f
llama : allow overriding GGUF metadata when loading model (#4092)
|
2 vuotta sitten |
 MaggotHATE
|
52c8bc3cf3
sampling : custom samplers order (#4285)
|
2 vuotta sitten |
|
Georgi Gerganov
|
6b0a7420d0
llama : KV cache view API + better KV cache management (#4170)
|
2 vuotta sitten |
 Seb C
|
881800d1f0
main : Add ChatML functionality to main example (#4046)
|
2 vuotta sitten |
|
Kerfuffle
|
91f6499393
Respect tokenizer.ggml.add_bos_token value when tokenizing (#4040)
|
2 vuotta sitten |
|
Georgi Gerganov
|
8f961abdc4
speculative : change default p_accept to 0.5 + CLI args (#3919)
|
2 vuotta sitten |
|
Georgi Gerganov
|
05816027d6
common : YAYF (yet another YARN fix) (#3925)
|
2 vuotta sitten |
 cebtenzzre
|
b12fa0d1c1
build : link against build info instead of compiling against it (#3879)
|
2 vuotta sitten |
|
cebtenzzre
|
898aeca90a
llama : implement YaRN RoPE scaling (#2268)
|
2 vuotta sitten |
 bandoti
|
0e40806c1c
common : allow caller to handle help/argument exceptions (#3715)
|
2 vuotta sitten |
|
Georgi Gerganov
|
d1031cf49c
sampling : refactor init to use llama_sampling_params (#3696)
|
2 vuotta sitten |
|
Georgi Gerganov
|
0e89203b51
speculative : add tree-based sampling example (#3624)
|
2 vuotta sitten |
 staviq
|
1a159553f9
tokenizer : special token handling (#3538)
|
2 vuotta sitten |
 M. Yusuf Sarıgöz
|
370359e5ba
examples: support LLaVA v1.5 (multimodal model) (#3436)
|
2 vuotta sitten |
|
Kerfuffle
|
70c29da118
common : fix mirostat state when using multiple sequences (#3543)
|
2 vuotta sitten |
