diff --git a/.gitignore b/.gitignore index 919393032..c26d82a74 100644 --- a/.gitignore +++ b/.gitignore @@ -62,6 +62,11 @@ perf-*.txt examples/jeopardy/results.txt + +pyproject.toml +poetry.lock +poetry.toml + # Test binaries tests/test-double-float tests/test-grad0 @@ -69,4 +74,4 @@ tests/test-opt tests/test-quantize-fns tests/test-quantize-perf tests/test-sampling -tests/test-tokenizer-0 +tests/test-tokenizer-0 \ No newline at end of file diff --git a/Makefile b/Makefile index 4f8c4b37e..1ea3c4562 100644 --- a/Makefile +++ b/Makefile @@ -127,7 +127,7 @@ endif # Architecture specific # TODO: probably these flags need to be tweaked on some architectures # feel free to update the Makefile for your architecture and send a pull request or issue -ifeq ($(UNAME_M),$(filter $(UNAME_M),x86_64 i686)) +ifeq ($(UNAME_M),$(filter $(UNAME_M),x86_64 i686 amd64)) # Use all CPU extensions that are available: CFLAGS += -march=native -mtune=native CXXFLAGS += -march=native -mtune=native diff --git a/examples/llama2-13b.sh b/examples/llama2-13b.sh new file mode 100755 index 000000000..92b3f6dd8 --- /dev/null +++ b/examples/llama2-13b.sh @@ -0,0 +1,18 @@ +#!/bin/bash + +# +# Temporary script - will be removed in the future +# + +cd `dirname $0` +cd .. + +./main -m models/available/Llama2/13B/llama-2-13b.ggmlv3.q4_0.bin \ + --color \ + --ctx_size 2048 \ + -n -1 \ + -ins -b 256 \ + --top_k 10000 \ + --temp 0.2 \ + --repeat_penalty 1.1 \ + -t 8 diff --git a/examples/llama2.sh b/examples/llama2.sh new file mode 100755 index 000000000..221b37553 --- /dev/null +++ b/examples/llama2.sh @@ -0,0 +1,18 @@ +#!/bin/bash + +# +# Temporary script - will be removed in the future +# + +cd `dirname $0` +cd .. + +./main -m models/available/Llama2/7B/llama-2-7b.ggmlv3.q4_0.bin \ + --color \ + --ctx_size 2048 \ + -n -1 \ + -ins -b 256 \ + --top_k 10000 \ + --temp 0.2 \ + --repeat_penalty 1.1 \ + -t 8