Commit History

Autor SHA1 Mensaxe Data
  Roland 2d770505a8 llama : remove mtest (#3177) %!s(int64=2) %!d(string=hai) anos
  Cebtenzzre e64f5b5578 examples : make n_ctx warning work again (#3066) %!s(int64=2) %!d(string=hai) anos
  Przemysław Pawełczyk cb6c44c5e0 build : do not use _GNU_SOURCE gratuitously (#2035) %!s(int64=2) %!d(string=hai) anos
  Cebtenzzre 00d62adb79 fix some warnings from gcc and clang-tidy (#3038) %!s(int64=2) %!d(string=hai) anos
  Georgi Gerganov e36ecdccc8 build : on Mac OS enable Metal by default (#2901) %!s(int64=2) %!d(string=hai) anos
  Georgi Gerganov 47068e5170 speculative : PoC for speeding-up inference via speculative sampling (#2926) %!s(int64=2) %!d(string=hai) anos
  Georgi Gerganov 8f429fa511 perplexity : fix ETA by warming up the model with an empty run %!s(int64=2) %!d(string=hai) anos
  staviq 8341a25957 main : log file (#2748) %!s(int64=2) %!d(string=hai) anos
  Johannes Gäßler 6b73ef1201 YAML result logging + preset script (#2657) %!s(int64=2) %!d(string=hai) anos
  Georgi Gerganov edd4c14817 llama : more tokenizer fixes (#2810) %!s(int64=2) %!d(string=hai) anos
  Dr. Tom Murphy VII Ph.D 72f895c923 main : fix bug (penalize_nl=false doesn't work) + suppress warning on mingw (#1528) %!s(int64=2) %!d(string=hai) anos
  klosax 2ba83c8685 Fix spm whitespaces (#2806) %!s(int64=2) %!d(string=hai) anos
  Kerfuffle 7694adda8d Fix for main example getting stuck when -n -2 and --interactive (#2767) %!s(int64=2) %!d(string=hai) anos
  Georgi Gerganov cf658adc83 llm : add Falcon support (#2717) %!s(int64=2) %!d(string=hai) anos
  klosax 5290c38e6e main : insert bos if no tokens (#2727) %!s(int64=2) %!d(string=hai) anos
  Georgi Gerganov 6381d4e110 gguf : new file format with flexible meta data (beta) (#2398) %!s(int64=2) %!d(string=hai) anos
  Christian Demsar e59fcb2bc1 Add --n-predict -2 for stopping generation on full context (#2565) %!s(int64=2) %!d(string=hai) anos
  DannyDaemonic 3498588e0f Add --simple-io option for subprocesses and break out console.h and cpp (#1558) %!s(int64=2) %!d(string=hai) anos
  Xiao-Yong Jin 0c06204fb3 main : add `--in-prefix-bos` to prefix BOS to user inputs; keep EOS (#2304) %!s(int64=2) %!d(string=hai) anos
  Evan Jones 84e09a7d8b llama : add grammar-based sampling (#1773) %!s(int64=2) %!d(string=hai) anos
  Georgi Gerganov e76d630df1 llama : grouped-query attention + LLaMAv2 70B support (#2276) %!s(int64=2) %!d(string=hai) anos
  Georgi Gerganov b47b8a9cfe llama : optimize memory buffers (#2325) %!s(int64=2) %!d(string=hai) anos
  Guillaume "Vermeille" Sanchez ab0e26bdfb llama : remove cfg smooth factor as it is only a reparameterization of the guidance scale (#2280) %!s(int64=2) %!d(string=hai) anos
  Xiao-Yong Jin 6e7cca4047 llama : add custom RoPE (#2054) %!s(int64=2) %!d(string=hai) anos
  Bach Le c9c74b4e3f llama : add classifier-free guidance (#2135) %!s(int64=2) %!d(string=hai) anos
  Evan Miller 5656d10599 mpi : add support for distributed inference via MPI (#2099) %!s(int64=2) %!d(string=hai) anos
  Judd 36680f6e40 convert : update for baichuan (#2081) %!s(int64=2) %!d(string=hai) anos
  Howard Su b8c8dda75f Use unsigned for random seed (#2006) %!s(int64=2) %!d(string=hai) anos
  zrm b853d45601 ggml : add NUMA support (#1556) %!s(int64=2) %!d(string=hai) anos
  Didzis Gosko 527b6fba1d llama : make model stateless and context stateful (llama_state) (#1797) %!s(int64=2) %!d(string=hai) anos