| .. |
|
baby-llama
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 rok temu |
|
batched
|
da3913d8f9
batched: fix n_predict parameter (#8527)
|
1 rok temu |
|
batched-bench
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 rok temu |
|
batched.swift
|
213701b51a
Detokenizer fixes (#8039)
|
1 rok temu |
|
benchmark
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 rok temu |
|
convert-llama2c-to-ggml
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 rok temu |
|
cvector-generator
|
49c03c79cd
cvector: better prompt handling, add "mean vector" method (#8069)
|
1 rok temu |
|
deprecation-warning
|
e500d6135a
Deprecation warning to assist with migration to new binary names (#8283)
|
1 rok temu |
|
embedding
|
07a3fc0608
Removes multiple newlines at the end of files that is breaking the editorconfig step of CI. (#8258)
|
1 rok temu |
|
eval-callback
|
71c1121d11
examples : sprintf -> snprintf (#8434)
|
1 rok temu |
|
export-lora
|
de280085e7
examples : Fix `llama-export-lora` example (#8607)
|
1 rok temu |
|
finetune
|
3fd62a6b1c
py : type-check all Python scripts with Pyright (#8341)
|
1 rok temu |
|
gbnf-validator
|
938943cdbf
llama : move vocab, grammar and sampling into separate files (#8508)
|
1 rok temu |
|
gguf
|
07283b1a90
gguf : handle null name during init (#8587)
|
1 rok temu |
|
gguf-hash
|
1666f92dcd
gguf-hash : update clib.json to point to original xxhash repo (#8491)
|
1 rok temu |
|
gguf-split
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 rok temu |
|
gritlm
|
80ea089d77
llama : allow pooled embeddings on any model (#7477)
|
1 rok temu |
|
imatrix
|
4b0eff3df5
docs : Quantum -> Quantized (#8666)
|
1 rok temu |
|
infill
|
6f0dbf6ab0
infill : assert prefix/suffix tokens + remove old space logic (#8351)
|
1 rok temu |
|
jeopardy
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 rok temu |
|
llama-bench
|
1bdd8ae19f
[CANN] Add Ascend NPU backend (#6035)
|
1 rok temu |
|
llama.android
|
b7c11d36e6
examples: fix android example cannot be generated continuously (#8621)
|
1 rok temu |
|
llama.swiftui
|
69b9945b44
llama.swiftui: fix end of generation bug (#8268)
|
1 rok temu |
|
llava
|
1bdd8ae19f
[CANN] Add Ascend NPU backend (#6035)
|
1 rok temu |
|
lookahead
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 rok temu |
|
lookup
|
e02b597be3
lookup: fibonacci hashing, fix crashes (#8548)
|
1 rok temu |
|
main
|
96952e7181
llama : fix `llama_chat_format_single` for mistral (#8657)
|
1 rok temu |
|
main-cmake-pkg
|
07a3fc0608
Removes multiple newlines at the end of files that is breaking the editorconfig step of CI. (#8258)
|
1 rok temu |
|
parallel
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 rok temu |
|
passkey
|
61ecafa390
passkey : add short intro to README.md [no-ci] (#8317)
|
1 rok temu |
|
perplexity
|
5f2d4e60e2
ppl : fix n_seq_max for perplexity (#8277)
|
1 rok temu |
|
quantize
|
0efec57787
llama : valign + remove unused ftype (#8502)
|
1 rok temu |
|
quantize-stats
|
370b1f7e7a
ggml : minor naming changes (#8433)
|
1 rok temu |
|
retrieval
|
80ea089d77
llama : allow pooled embeddings on any model (#7477)
|
1 rok temu |
|
rpc
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 rok temu |
|
save-load-state
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 rok temu |
|
server
|
4b0eff3df5
docs : Quantum -> Quantized (#8666)
|
1 rok temu |
|
simple
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 rok temu |
|
speculative
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 rok temu |
|
sycl
|
07a3fc0608
Removes multiple newlines at the end of files that is breaking the editorconfig step of CI. (#8258)
|
1 rok temu |
|
tokenize
|
9a55ffe6fb
tokenize : add --no-parse-special option (#8423)
|
1 rok temu |
|
train-text-from-scratch
|
3fd62a6b1c
py : type-check all Python scripts with Pyright (#8341)
|
1 rok temu |
|
CMakeLists.txt
|
f7cab35ef9
gguf-hash: model wide and per tensor hashing using xxhash and sha1 (#8048)
|
1 rok temu |
|
Miku.sh
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 rok temu |
|
base-translate.sh
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 rok temu |
|
chat-13B.bat
|
d9ad104440
Create chat-13B.bat (#592)
|
2 lat temu |
|
chat-13B.sh
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 rok temu |
|
chat-persistent.sh
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 rok temu |
|
chat-vicuna.sh
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 rok temu |
|
chat.sh
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 rok temu |
|
convert_legacy_llama.py
|
672a6f1018
convert-*.py: GGUF Naming Convention Refactor and Metadata Override Refactor (#7499)
|
1 rok temu |
|
json_schema_pydantic_example.py
|
3fd62a6b1c
py : type-check all Python scripts with Pyright (#8341)
|
1 rok temu |
|
json_schema_to_grammar.py
|
3fd62a6b1c
py : type-check all Python scripts with Pyright (#8341)
|
1 rok temu |
|
llama.vim
|
125d03a503
llama.vim : added api key support (#5090)
|
2 lat temu |
|
llm.vim
|
ad9ddcff6e
llm.vim : stop generation at multiple linebreaks, bind to <F2> (#2879)
|
2 lat temu |
|
pydantic_models_to_grammar.py
|
090fca7a07
pydantic : replace uses of __annotations__ with get_type_hints (#8474)
|
1 rok temu |
|
pydantic_models_to_grammar_examples.py
|
22f281aa16
examples : Rewrite pydantic_models_to_grammar_examples.py (#8493)
|
1 rok temu |
|
reason-act.sh
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 rok temu |
|
regex_to_grammar.py
|
e235b267a2
py : switch to snake_case (#8305)
|
1 rok temu |
|
server-llama2-13B.sh
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 rok temu |
|
server_embd.py
|
3fd62a6b1c
py : type-check all Python scripts with Pyright (#8341)
|
1 rok temu |
|
ts-type-to-grammar.sh
|
ab9a3240a9
JSON schema conversion: ⚡️ faster repetitions, min/maxLength for strings, cap number length (#6555)
|
1 rok temu |
Ujjawal Panchal
4b0eff3df5
docs : Quantum -> Quantized (#8666)