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.

Ivan Stepanov dd7eff57d8 llama : new sampling algorithms (#1126) ... * Sample interface, new samplers. New samplers: - locally typical sampling - tail free sampling - frequency and presence penalty - mirostat Ignore EOS fix: -inf should be used. * mirostat * Added --logit-bias and --no-penalize-nl, removed std::span * Use C++11, clarify llama API documentation, rename Mirostat parameters to --mirostat_lr and --mirostat_ent, add temperature sampling for Mirostat, simplify Mirostat sampling API parameters (removed N and *k) Use C++11, clarify llama API documentation, rename Mirostat parameters to --mirostat_lr and --mirostat_ent, add temperature sampling for Mirostat, simplify Mirostat sampling API parameters (removed N and *k) * Save and load example adjust * Tests * Windows build fix * Windows test fix		1 year ago
..
CMakeLists.txt	llama : new sampling algorithms (#1126)	1 year ago
test-double-float.c	all : be more strict about converting float to double (#458)	1 year ago
test-quantize-fns.cpp	ggml : add Q8_0 quantization format (rename the old one to Q8_1) (ARM NEON) (#1179)	1 year ago
test-quantize-perf.cpp	Fix CI: ARM NEON, quantization unit tests, editorconfig (#1122)	1 year ago
test-sampling.cpp	llama : new sampling algorithms (#1126)	1 year ago
test-tokenizer-0.cpp	llama : well-defined static initialization of complex objects (#927)	1 year ago