Home Esplora Aiuto
Accedi
cturan
/
llama.cpp
mirror da https://github.com/cturan/llama.cpp
1
0
Forka 0
File Problemi 0 Wiki
Albero (Tree): 978ba3d83d
Rami (Branch) Tag
llama.cpp
/
examples
ardfork 978ba3d83d Server: Don't ignore llama.cpp params (#8754) 1 anno fa
..
baby-llama 01aae2b497 baby-llama : remove duplicate vector include 1 anno fa
batched da3913d8f9 batched: fix n_predict parameter (#8527) 1 anno fa
batched-bench ecf6b7f23e batched-bench : handle empty `-npl` (#8839) 1 anno fa
batched.swift 213701b51a Detokenizer fixes (#8039) 1 anno fa
benchmark 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 1 anno fa
convert-llama2c-to-ggml 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 1 anno fa
cvector-generator 49c03c79cd cvector: better prompt handling, add "mean vector" method (#8069) 1 anno fa
deprecation-warning be6d7c0791 examples : remove `finetune` and `train-text-from-scratch` (#8669) 1 anno fa
embedding 07a3fc0608 Removes multiple newlines at the end of files that is breaking the editorconfig step of CI. (#8258) 1 anno fa
eval-callback 2b1f616b20 ggml : reduce hash table reset cost (#8698) 1 anno fa
export-lora 41cd47caab examples : export-lora : fix issue with quantized base models (#8687) 1 anno fa
gbnf-validator 938943cdbf llama : move vocab, grammar and sampling into separate files (#8508) 1 anno fa
gguf 07283b1a90 gguf : handle null name during init (#8587) 1 anno fa
gguf-hash 1666f92dcd gguf-hash : update clib.json to point to original xxhash repo (#8491) 1 anno fa
gguf-split 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 1 anno fa
gritlm 80ea089d77 llama : allow pooled embeddings on any model (#7477) 1 anno fa
imatrix 2b1f616b20 ggml : reduce hash table reset cost (#8698) 1 anno fa
infill 6f0dbf6ab0 infill : assert prefix/suffix tokens + remove old space logic (#8351) 1 anno fa
jeopardy 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 1 anno fa
llama-bench 2b1f616b20 ggml : reduce hash table reset cost (#8698) 1 anno fa
llama.android b7c11d36e6 examples: fix android example cannot be generated continuously (#8621) 1 anno fa
llama.swiftui 69b9945b44 llama.swiftui: fix end of generation bug (#8268) 1 anno fa
llava 2b1f616b20 ggml : reduce hash table reset cost (#8698) 1 anno fa
lookahead 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 1 anno fa
lookup e02b597be3 lookup: fibonacci hashing, fix crashes (#8548) 1 anno fa
main 96952e7181 llama : fix `llama_chat_format_single` for mistral (#8657) 1 anno fa
main-cmake-pkg 07a3fc0608 Removes multiple newlines at the end of files that is breaking the editorconfig step of CI. (#8258) 1 anno fa
parallel 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 1 anno fa
passkey 61ecafa390 passkey : add short intro to README.md [no-ci] (#8317) 1 anno fa
perplexity 5f2d4e60e2 ppl : fix n_seq_max for perplexity (#8277) 1 anno fa
quantize 0efec57787 llama : valign + remove unused ftype (#8502) 1 anno fa
quantize-stats 370b1f7e7a ggml : minor naming changes (#8433) 1 anno fa
retrieval 80ea089d77 llama : allow pooled embeddings on any model (#7477) 1 anno fa
rpc f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
save-load-state 4c676c85e5 llama : refactor session file management (#8699) 1 anno fa
server 978ba3d83d Server: Don't ignore llama.cpp params (#8754) 1 anno fa
simple 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 1 anno fa
speculative 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 1 anno fa
sycl 07a3fc0608 Removes multiple newlines at the end of files that is breaking the editorconfig step of CI. (#8258) 1 anno fa
tokenize 2b1f616b20 ggml : reduce hash table reset cost (#8698) 1 anno fa
CMakeLists.txt be6d7c0791 examples : remove `finetune` and `train-text-from-scratch` (#8669) 1 anno fa
Miku.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 1 anno fa
base-translate.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 1 anno fa
chat-13B.bat d9ad104440 Create chat-13B.bat (#592) 2 anni fa
chat-13B.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 1 anno fa
chat-persistent.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 1 anno fa
chat-vicuna.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 1 anno fa
chat.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 1 anno fa
convert_legacy_llama.py 672a6f1018 convert-*.py: GGUF Naming Convention Refactor and Metadata Override Refactor (#7499) 1 anno fa
json_schema_pydantic_example.py 3fd62a6b1c py : type-check all Python scripts with Pyright (#8341) 1 anno fa
json_schema_to_grammar.py 3fd62a6b1c py : type-check all Python scripts with Pyright (#8341) 1 anno fa
llama.vim 125d03a503 llama.vim : added api key support (#5090) 2 anni fa
llm.vim ad9ddcff6e llm.vim : stop generation at multiple linebreaks, bind to <F2> (#2879) 2 anni fa
pydantic_models_to_grammar.py 090fca7a07 pydantic : replace uses of __annotations__ with get_type_hints (#8474) 1 anno fa
pydantic_models_to_grammar_examples.py 22f281aa16 examples : Rewrite pydantic_models_to_grammar_examples.py (#8493) 1 anno fa
reason-act.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 1 anno fa
regex_to_grammar.py e235b267a2 py : switch to snake_case (#8305) 1 anno fa
server-llama2-13B.sh 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 1 anno fa
server_embd.py 3fd62a6b1c py : type-check all Python scripts with Pyright (#8341) 1 anno fa
ts-type-to-grammar.sh ab9a3240a9 JSON schema conversion: ⚡️ faster repetitions, min/maxLength for strings, cap number length (#6555) 1 anno fa