 Radoslav Gerganov
|
5e31828d3e
ggml : add RPC backend (#6829)
|
1 年之前 |
 Justine Tunney
|
4e3880978f
Fix memory bug in grammar parser (#7194)
|
1 年之前 |
 HanishKVC
|
f89fe2732c
Main+: optionally allow special tokens from user in interactive mode (#7097)
|
1 年之前 |
 Johannes Gäßler
|
c12452c7ae
JSON: [key] -> .at(key), assert() -> GGML_ASSERT (#7143)
|
1 年之前 |
 Dawid Potocki
|
83330d8cd6
main : add --conversation / -cnv flag (#7108)
|
1 年之前 |
 viric
|
fcd84a0f5a
Fix Linux /sys cpu path to guess number of cores (#7064)
|
1 年之前 |
 Georgi Gerganov
|
9c67c2773d
ggml : add Flash Attention (#5021)
|
1 年之前 |
 Olivier Chafik
|
8843a98c2b
Improve usability of --model-url & related flags (#6930)
|
1 年之前 |
 cpumaxx
|
ffe666572f
llava-cli : multiple images (#6969)
|
1 年之前 |
|
Georgi Gerganov
|
f4ab2a4147
llama : fix BPE pre-tokenization (#6920)
|
1 年之前 |
 Pierrick Hymbert
|
0c4d489e29
quantize: add imatrix and dataset metadata in GGUF (#6658)
|
1 年之前 |
 slaren
|
017e6999b5
add basic tensor data validation function (#6884)
|
1 年之前 |
 Kyle Mistele
|
37246b1031
common : revert showing control tokens by default for server (#6860)
|
1 年之前 |
|
Johannes Gäßler
|
28103f4832
Server: fix seed for multiple slots (#6835)
|
1 年之前 |
|
Georgi Gerganov
|
40f74e4d73
llama : add option to render special/control tokens (#6807)
|
1 年之前 |
|
Georgi Gerganov
|
aed82f6837
common : try to fix Android CI (#6780)
|
1 年之前 |
|
Justine Tunney
|
8cc91dc63c
ggml : add llamafile sgemm (#6414)
|
1 年之前 |
|
Olivier Chafik
|
7593639ce3
`main`: add --json-schema / -j flag (#6659)
|
1 年之前 |
|
Pierrick Hymbert
|
b804b1ef77
eval-callback: Example how to use eval callback for debugging (#6576)
|
1 年之前 |
 Jared Van Bortel
|
1b67731e18
BERT tokenizer fixes (#6498)
|
1 年之前 |
 Jan Boon
|
beea6e1b16
llama : save and restore kv cache for single seq id (#6341)
|
1 年之前 |
 Daniel Bevenius
|
4bcd6b959c
common: remove duplicate check for curl (#6471)
|
1 年之前 |
 Sigbjørn Skjæret
|
e562b9714b
common : change --no-penalize-nl to --penalize-nl (#6334)
|
1 年之前 |
|
slaren
|
280345968d
cuda : rename build flag to LLAMA_CUDA (#6299)
|
1 年之前 |
 Minsoo Cheong
|
64e7b47c69
examples : add "retrieval" (#6193)
|
1 年之前 |
|
Pierrick Hymbert
|
f482bb2e49
common: llama_load_model_from_url split support (#6192)
|
1 年之前 |
|
Johannes Gäßler
|
50ccaf5eac
lookup: complement data from context with general text statistics (#5479)
|
1 年之前 |
|
Georgi Gerganov
|
56a00f0a2f
common : default --hf-file to --model (#6234)
|
1 年之前 |
|
Georgi Gerganov
|
80bd33bc2c
common : add HF arg helpers (#6234)
|
1 年之前 |
|
Georgi Gerganov
|
95d576b48e
metal : pad n_ctx by 32 (#6177)
|
1 年之前 |
