root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 02:44:36 +00:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

server: add rms_norm_eps parameter (#2380)

Browse Source
This commit is contained in:
slaren 2023-07-25 11:36:17 +02:00 committed by GitHub
parent c798308e3a
commit d5512b782b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 9 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
examples/server/server.cpp
View File

@ -609,6 +609,7 @@ static void server_print_usage(const char *argv0, const gpt_params &params,
fprintf(stdout, " -t N, --threads N number of threads to use during computation (default: %d)\n", params.n_threads); fprintf(stdout, " -t N, --threads N number of threads to use during computation (default: %d)\n", params.n_threads);
fprintf(stdout, " -c N, --ctx-size N size of the prompt context (default: %d)\n", params.n_ctx); fprintf(stdout, " -c N, --ctx-size N size of the prompt context (default: %d)\n", params.n_ctx);
fprintf(stdout, " -gqa N, --gqa N grouped-query attention factor (TEMP!!! use 8 for LLaMAv2 70B) (default: %d)\n", params.n_gqa); fprintf(stdout, " -gqa N, --gqa N grouped-query attention factor (TEMP!!! use 8 for LLaMAv2 70B) (default: %d)\n", params.n_gqa);
fprintf(stdout, " -eps N, --rms-norm-eps N rms norm eps (TEMP!!! use 1e-5 for LLaMAv2) (default: %.1e)\n", params.rms_norm_eps);
fprintf(stdout, " --rope-freq-base N RoPE base frequency (default: %.1f)\n", params.rope_freq_base); fprintf(stdout, " --rope-freq-base N RoPE base frequency (default: %.1f)\n", params.rope_freq_base);
fprintf(stdout, " --rope-freq-scale N RoPE frequency scaling factor (default: %g)\n", params.rope_freq_scale); fprintf(stdout, " --rope-freq-scale N RoPE frequency scaling factor (default: %g)\n", params.rope_freq_scale);
fprintf(stdout, " -b N, --batch-size N batch size for prompt processing (default: %d)\n", params.n_batch); fprintf(stdout, " -b N, --batch-size N batch size for prompt processing (default: %d)\n", params.n_batch);
@ -734,6 +735,14 @@ static void server_params_parse(int argc, char **argv, server_params &sparams,
} }
params.n_gqa = std::stoi(argv[i]); params.n_gqa = std::stoi(argv[i]);
} }
else if (arg == "-eps" || arg == "--rms-norm-eps") {
if (++i >= argc)
{
invalid_param = true;
break;
}
params.rms_norm_eps = std::stof(argv[i]);
}
else if (arg == "--rope-freq-base") else if (arg == "--rope-freq-base")
{ {
if (++i >= argc) if (++i >= argc)