vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

help : fix gqa value for 70B

Browse source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2023-07-23 12:35:55 +03:00
parent c594992d6a
commit 8194d591b2
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/common.cpp
View file

@ -493,7 +493,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
fprintf(stderr, " -n N, --n-predict N number of tokens to predict (default: %d, -1 = infinity)\n", params.n_predict);
fprintf(stderr, " -c N, --ctx-size N size of the prompt context (default: %d)\n", params.n_ctx);
fprintf(stderr, " -b N, --batch-size N batch size for prompt processing (default: %d)\n", params.n_batch);
fprintf(stderr, " -gqa N, --gqa N grouped-query attention factor (TEMP!!! use 7 for LLaMAv2 70B) (default: %d)\n", params.n_gqa);
fprintf(stderr, " -gqa N, --gqa N grouped-query attention factor (TEMP!!! use 8 for LLaMAv2 70B) (default: %d)\n", params.n_gqa);
fprintf(stderr, " --top-k N top-k sampling (default: %d, 0 = disabled)\n", params.top_k);
fprintf(stderr, " --top-p N top-p sampling (default: %.1f, 1.0 = disabled)\n", (double)params.top_p);
fprintf(stderr, " --tfs N tail free sampling, parameter z (default: %.1f, 1.0 = disabled)\n", (double)params.tfs_z);