diff options
| author | Kawrakow <48489457+ikawrakow@users.noreply.github.com> | 2023-07-25 18:35:53 +0300 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-07-25 18:35:53 +0300 |
| commit | eb542d39324574a6778fad9ba9e34ba7a14a82a3 (patch) | |
| tree | 3009fde3ceb24f19dfbb2da7c072942ba06eaa83 /examples/common.h | |
| parent | 07aaa0f63fccaeab099b3a732abda20b921bc5a5 (diff) | |
Add LLAMA_DEFAULT_RMS_EPS so we can change the default (#2384)
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'examples/common.h')
| -rw-r--r-- | examples/common.h | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/examples/common.h b/examples/common.h index 2d87c923..672dcf77 100644 --- a/examples/common.h +++ b/examples/common.h @@ -34,7 +34,7 @@ struct gpt_params { int32_t main_gpu = 0; // the GPU that is used for scratch and small tensors 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. - float rms_norm_eps = 1e-6; // rms norm epsilon + float rms_norm_eps = LLAMA_DEFAULT_RMS_EPS; // rms norm epsilon float rope_freq_base = 10000.0f; // RoPE base frequency float rope_freq_scale = 1.0f; // RoPE frequency scaling factor |