CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-04 09:32:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into compilade/refactor-kv-cache

Browse Source
This commit is contained in:
Francis Couture-Harpin
2024-06-30 15:31:25 -04:00
parent 33425a7e1e 9ef0780062
commit 10c3c419e9
518 changed files with 78202 additions and 66427 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/perplexity/CMakeLists.txt
View File

@@ -1,4 +1,4 @@
set(TARGET perplexity)
set(TARGET llama-perplexity)
add_executable(${TARGET} perplexity.cpp)
install(TARGETS ${TARGET} RUNTIME)
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})

2
examples/perplexity/perplexity.cpp
View File

@@ -476,7 +476,7 @@ static results_perplexity perplexity(llama_context * ctx, const gpt_params & par
}
// Download: https://huggingface.co/datasets/ggml-org/ci/resolve/main/wikitext-2-raw-v1.zip
// Run `./perplexity -m models/7B/ggml-model-q4_0.bin -f wiki.test.raw`
// Run `./llama-perplexity -m models/7B/ggml-model-q4_0.bin -f wiki.test.raw`
// Output: `perplexity: 13.5106 [114/114]`
// BOS tokens will be added for each chunk before eval