llama_cpp_for_radxa_dragon_.../examples
Spencer Sutton 5bf2a27718
ggml : remove src0 and src1 from ggml_tensor and rename opt to src (#2178)
* Add ggml changes

* Update train-text-from-scratch for change

* mpi : adapt to new ggml_tensor->src

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-07-11 19:31:10 +03:00
..
baby-llama ggml : change ggml_graph_compute() API to not require context (#1999) 2023-07-07 19:24:01 +03:00
benchmark ggml : change ggml_graph_compute() API to not require context (#1999) 2023-07-07 19:24:01 +03:00
embd-input mpi : add support for distributed inference via MPI (#2099) 2023-07-10 18:49:56 +03:00
embedding mpi : add support for distributed inference via MPI (#2099) 2023-07-10 18:49:56 +03:00
jeopardy
main llama : add classifier-free guidance (#2135) 2023-07-11 19:18:43 +03:00
metal ggml : change ggml_graph_compute() API to not require context (#1999) 2023-07-07 19:24:01 +03:00
perplexity mpi : add support for distributed inference via MPI (#2099) 2023-07-10 18:49:56 +03:00
quantize mpi : add support for distributed inference via MPI (#2099) 2023-07-10 18:49:56 +03:00
quantize-stats ggml : generalize quantize_fns for simpler FP16 handling (#1237) 2023-07-05 19:13:06 +03:00
save-load-state llama : make model stateless and context stateful (llama_state) (#1797) 2023-06-24 11:47:58 +03:00
server Support using mmap when applying LoRA (#2095) 2023-07-11 22:37:01 +08:00
simple mpi : add support for distributed inference via MPI (#2099) 2023-07-10 18:49:56 +03:00
train-text-from-scratch ggml : remove src0 and src1 from ggml_tensor and rename opt to src (#2178) 2023-07-11 19:31:10 +03:00
alpaca.sh alpaca.sh : update model file name (#2074) 2023-07-06 19:17:50 +03:00
chat-13B.bat
chat-13B.sh
chat-persistent.sh
chat-vicuna.sh
chat.sh
CMakeLists.txt llama : support input embeddings directly (#1910) 2023-06-28 18:53:37 +03:00
common.cpp llama : add classifier-free guidance (#2135) 2023-07-11 19:18:43 +03:00
common.h llama : add classifier-free guidance (#2135) 2023-07-11 19:18:43 +03:00
gpt4all.sh
Miku.sh
reason-act.sh