diff options
Diffstat (limited to 'examples/imatrix/README.md')
| -rw-r--r-- | examples/imatrix/README.md | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/examples/imatrix/README.md b/examples/imatrix/README.md index 866ca9f5..38b36ee5 100644 --- a/examples/imatrix/README.md +++ b/examples/imatrix/README.md @@ -6,7 +6,7 @@ More information is available here: https://github.com/ggerganov/llama.cpp/pull/ ## Usage ``` -./imatrix \ +./llama-imatrix \ -m model.gguf -f some-text.txt [-o imatrix.dat] [--process-output] [--verbosity 1] \ [--no-ppl] [--chunk 123] [--output-frequency 10] [--save-frequency 0] \ [--in-file imatrix-prev-0.dat --in-file imatrix-prev-1.dat ...] @@ -28,8 +28,8 @@ For faster computation, make sure to use GPU offloading via the `-ngl` argument LLAMA_CUDA=1 make -j # generate importance matrix (imatrix.dat) -./imatrix -m ggml-model-f16.gguf -f train-data.txt -ngl 99 +./llama-imatrix -m ggml-model-f16.gguf -f train-data.txt -ngl 99 # use the imatrix to perform a Q4_K_M quantization -./quantize --imatrix imatrix.dat ggml-model-f16.gguf ./ggml-model-q4_k_m.gguf q4_k_m +./llama-quantize --imatrix imatrix.dat ggml-model-f16.gguf ./ggml-model-q4_k_m.gguf q4_k_m ``` |