Commit History

Autor SHA1 Mensaxe Data
  Cebtenzzre 849408957c tests : add a C compliance test (#2848) %!s(int64=2) %!d(string=hai) anos
  Georgi Gerganov edd4c14817 llama : more tokenizer fixes (#2810) %!s(int64=2) %!d(string=hai) anos
  Georgi Gerganov cf658adc83 llm : add Falcon support (#2717) %!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
  drbh 7cf54e1f74 tests : adds simple llama grammar tests (#2618) %!s(int64=2) %!d(string=hai) anos
  drbh ee77efea2a test : add simple grammar parsing tests (#2594) %!s(int64=2) %!d(string=hai) anos
  Eve 81844fbcfd tests : Fix compilation warnings (Linux/GCC) (#2451) %!s(int64=2) %!d(string=hai) anos
  wzy b1f4290953 cmake : install targets (#2256) %!s(int64=2) %!d(string=hai) anos
  Qingyou Meng 1d656d6360 ggml : change ggml_graph_compute() API to not require context (#1999) %!s(int64=2) %!d(string=hai) anos
  xaedes f954edda93 ggml : implement backward pass for llama + small training-llama-from-scratch example (#1360) %!s(int64=2) %!d(string=hai) anos
  Ivan Stepanov dd7eff57d8 llama : new sampling algorithms (#1126) %!s(int64=2) %!d(string=hai) anos
  unbounded 5f939498d5 ggml : unit test for quantization functions (#953) %!s(int64=2) %!d(string=hai) anos
  Stephan Walter 436e561931 all : be more strict about converting float to double (#458) %!s(int64=2) %!d(string=hai) anos
  Georgi Gerganov a316a425d0 Overhaul the examples structure %!s(int64=2) %!d(string=hai) anos
  Stephan Walter 69c92298a9 Deduplicate q4 quantization functions (#383) %!s(int64=2) %!d(string=hai) anos
  Georgi Gerganov f5a77a629b Introduce C-style API (#370) %!s(int64=2) %!d(string=hai) anos
  Georgi Gerganov eb34620aec Add tokenizer test + revert to C++11 (#355) %!s(int64=2) %!d(string=hai) anos