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

2023-04-29 08:34:41 +03:00

..

CMakeLists.txt

llama : new sampling algorithms (#1126)

2023-04-29 08:34:41 +03:00

test-double-float.c

all : be more strict about converting float to double (#458)

2023-03-28 19:48:20 +03:00

test-quantize-fns.cpp

ggml : add Q8_0 quantization format (rename the old one to Q8_1) (ARM NEON) (#1179)

2023-04-25 23:40:51 +03:00

test-quantize-perf.cpp

Fix CI: ARM NEON, quantization unit tests, editorconfig (#1122)

2023-04-22 10:54:13 +00:00

test-sampling.cpp

llama : new sampling algorithms (#1126)

2023-04-29 08:34:41 +03:00

test-tokenizer-0.cpp

llama : well-defined static initialization of complex objects (#927)

2023-04-17 17:41:53 +03:00