CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

quantize : fix typo in usage help of quantize.cpp (#9145)

Browse Source
This commit is contained in:
João Dinis Ferreira
2024-08-24 07:22:45 +01:00
committed by GitHub
parent 3ba780e2a8
commit 8f824ffe8e
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/quantize/quantize.cpp
View File

@@ -104,7 +104,7 @@ static void usage(const char * executable) {
printf(" --exclude-weights tensor_name: use importance matrix for this/these tensor(s)\n"); printf(" --exclude-weights tensor_name: use importance matrix for this/these tensor(s)\n");
printf(" --output-tensor-type ggml_type: use this ggml_type for the output.weight tensor\n"); printf(" --output-tensor-type ggml_type: use this ggml_type for the output.weight tensor\n");
printf(" --token-embedding-type ggml_type: use this ggml_type for the token embeddings tensor\n"); printf(" --token-embedding-type ggml_type: use this ggml_type for the token embeddings tensor\n");
printf(" --keep-split: will generate quatized model in the same shards as input"); printf(" --keep-split: will generate quantized model in the same shards as input\n");
printf(" --override-kv KEY=TYPE:VALUE\n"); printf(" --override-kv KEY=TYPE:VALUE\n");
printf(" Advanced option to override model metadata by key in the quantized model. May be specified multiple times.\n"); printf(" Advanced option to override model metadata by key in the quantized model. May be specified multiple times.\n");
printf("Note: --include-weights and --exclude-weights cannot be used together\n"); printf("Note: --include-weights and --exclude-weights cannot be used together\n");