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

fix freq_base/scale default to model value

Browse source
This commit is contained in:
slaren 2023-09-21 20:20:42 +02:00
parent 39f4afac20
commit f28e4953a8
2 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

2
common/common.cpp
View file

@ -621,7 +621,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
printf(" -f FNAME, --file FNAME\n");
printf(" prompt file to start generation.\n");
printf(" -n N, --n-predict N number of tokens to predict (default: %d, -1 = infinity, -2 = until context filled)\n", params.n_predict);
printf(" -c N, --ctx-size N size of the prompt context (default: %d)\n", params.n_ctx);
printf(" -c N, --ctx-size N size of the prompt context (default: %d, 0 = loaded from model)\n", params.n_ctx);
printf(" -b N, --batch-size N batch size for prompt processing (default: %d)\n", params.n_batch);
printf(" --top-k N top-k sampling (default: %d, 0 = disabled)\n", params.top_k);
printf(" --top-p N top-p sampling (default: %.1f, 1.0 = disabled)\n", (double)params.top_p);

4
common/common.h
View file

@ -48,8 +48,8 @@ struct gpt_params {
float tensor_split[LLAMA_MAX_DEVICES] = {0}; // how split tensors should be distributed across GPUs
int32_t n_probs = 0; // if greater than 0, output the probabilities of top n_probs tokens.
int32_t n_beams = 0; // if non-zero then use beam search of given width.
float rope_freq_base = 10000.0f; // RoPE base frequency
float rope_freq_scale = 1.0f; // RoPE frequency scaling factor
float rope_freq_base = 0.0f; // RoPE base frequency
float rope_freq_scale = 0.0f; // RoPE frequency scaling factor
// sampling parameters
int32_t top_k = 40; // <= 0 to use vocab size