You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
llama.cpp/examples
unbounded 62cfc54f77
Add quantize-stats command for testing quantization (#728)
Command that calculates some statistics over the errors introduced by
quantization, like mean square error, max error and some percentile errors for layer
weights. Should be useful for testing quantization improvements.

Exposes some internal state from ggml and llama for testing
2 years ago
..
embedding llama : fix linkage with mingw (#551) 2 years ago
main Do not crash when it has nothing to say. (#796) 2 years ago
perplexity llama : fix linkage with mingw (#551) 2 years ago
quantize Fix ggml_init_params in quantize 2 years ago
quantize-stats Add quantize-stats command for testing quantization (#728) 2 years ago
CMakeLists.txt Add quantize-stats command for testing quantization (#728) 2 years ago
Miku.sh miku.sh : add executable bit (#780) 2 years ago
alpaca.sh Move chat scripts into "./examples" 2 years ago
chat-13B.bat Create chat-13B.bat (#592) 2 years ago
chat-13B.sh Move chat scripts into "./examples" 2 years ago
chat.sh If n_predict == -1, generate forever 2 years ago
common.cpp fix default params for examples/main (#697) 2 years ago
common.h main.cpp fixes, refactoring (#571) 2 years ago
gpt4all.sh examples : add gpt4all script (#658) 2 years ago
reason-act.sh add example of re-act pattern (#583) 2 years ago