 jaime-m-p
|
213701b51a
Detokenizer fixes (#8039)
|
il y a 1 an |
 Douglas Hanley
|
d12f781074
llama : streamline embeddings from "non-embedding" models (#8087)
|
il y a 1 an |
 Clint Herron
|
07a3fc0608
Removes multiple newlines at the end of files that is breaking the editorconfig step of CI. (#8258)
|
il y a 1 an |
 Xuan Son Nguyen
|
9ef0780062
Fix new line issue with chat template, disable template when in-prefix/suffix is set (#8203)
|
il y a 1 an |
 Sigbjørn Skjæret
|
38373cfbab
Add SPM infill support (#8016)
|
il y a 1 an |
|
Xuan Son Nguyen
|
16791b8f0b
Add chatml fallback for cpp `llama_chat_apply_template` (#8160)
|
il y a 1 an |
|
Xuan Son Nguyen
|
49c03c79cd
cvector: better prompt handling, add "mean vector" method (#8069)
|
il y a 1 an |
|
Xuan Son Nguyen
|
48e6b92cc3
Add chat template support for llama-cli (#8068)
|
il y a 1 an |
 Yann Follet
|
646ef4a9cf
embedding : more cli arguments (#7458)
|
il y a 1 an |
 Frank Mai
|
b96f9afb0d
chore: clean useless beam search param (#7985)
|
il y a 1 an |
|
Xuan Son Nguyen
|
0c7b3595b9
Add `cvector-generator` example (#7514)
|
il y a 1 an |
 Olivier Chafik
|
d4d915d351
url: save -mu downloads to new cache location (#7826)
|
il y a 1 an |
 sasha0552
|
7a16ce7db2
server : smart slot selection using Longest Common Prefix (#7728)
|
il y a 1 an |
 Georgi Gerganov
|
ee459f40f6
server : fix --threads-http arg (#7801)
|
il y a 1 an |
|
Georgi Gerganov
|
f83351f9a6
imatrix : migrate to gpt_params (#7771)
|
il y a 1 an |
|
Georgi Gerganov
|
1442677f92
common : refactor cli arg parsing (#7675)
|
il y a 1 an |
 Brian
|
d298382ad9
main: replace --no-special with --special (#7534)
|
il y a 1 an |
 Justine Tunney
|
00c6390793
main : don't print special tokens with --grammar (#6923)
|
il y a 1 an |
|
Georgi Gerganov
|
6ff13987ad
common : normalize naming style (#7462)
|
il y a 1 an |
 Amir
|
11474e756d
examples: cache hf model when --model not provided (#7353)
|
il y a 1 an |
 Radoslav Gerganov
|
5e31828d3e
ggml : add RPC backend (#6829)
|
il y a 1 an |
 HanishKVC
|
f89fe2732c
Main+: optionally allow special tokens from user in interactive mode (#7097)
|
il y a 1 an |
 Dawid Potocki
|
83330d8cd6
main : add --conversation / -cnv flag (#7108)
|
il y a 1 an |
 Johannes Gäßler
|
a8f9b07631
perplexity: more statistics, added documentation (#6936)
|
il y a 1 an |
|
Georgi Gerganov
|
9c67c2773d
ggml : add Flash Attention (#5021)
|
il y a 1 an |
|
Olivier Chafik
|
8843a98c2b
Improve usability of --model-url & related flags (#6930)
|
il y a 1 an |
 cpumaxx
|
ffe666572f
llava-cli : multiple images (#6969)
|
il y a 1 an |
|
Georgi Gerganov
|
f4ab2a4147
llama : fix BPE pre-tokenization (#6920)
|
il y a 1 an |
 Pierrick Hymbert
|
0c4d489e29
quantize: add imatrix and dataset metadata in GGUF (#6658)
|
il y a 1 an |
 slaren
|
017e6999b5
add basic tensor data validation function (#6884)
|
il y a 1 an |
