diff options
| author | aditya <bluenerd@protonmail.com> | 2023-08-10 12:32:35 +0530 |
|---|---|---|
| committer | aditya <bluenerd@protonmail.com> | 2023-08-10 12:32:35 +0530 |
| commit | a9ff78b3f48dc9f81943c41531c4959ce7e2ae9d (patch) | |
| tree | 49ee8c3c9148038f04112802265d928ef1aba428 /examples/baby-llama/baby-llama.cpp | |
| parent | 2516af4cd61f509c995b4f78fdf123cba33f3509 (diff) | |
| parent | 916a9acdd0a411426690400ebe2bb7ce840a6bba (diff) | |
resolve merge conflict
Diffstat (limited to 'examples/baby-llama/baby-llama.cpp')
| -rw-r--r-- | examples/baby-llama/baby-llama.cpp | 24 |
1 files changed, 15 insertions, 9 deletions
diff --git a/examples/baby-llama/baby-llama.cpp b/examples/baby-llama/baby-llama.cpp index 4965881..6fa55b3 100644 --- a/examples/baby-llama/baby-llama.cpp +++ b/examples/baby-llama/baby-llama.cpp @@ -8,6 +8,12 @@ #pragma warning(disable: 4244 4267) // possible loss of data #endif +#ifdef LLAMA_DEFAULT_RMS_EPS +static const float rms_norm_eps = LLAMA_DEFAULT_RMS_EPS; +#else +static const float rms_norm_eps = 5e-6f; +#endif + float frand() { return (float)rand()/(float)RAND_MAX; } @@ -562,7 +568,7 @@ struct ggml_tensor * forward( // norm { // cur shape [n_embd,N,1,1] - cur = ggml_rms_norm(ctx0, inpL); + cur = ggml_rms_norm(ctx0, inpL, rms_norm_eps); // cur = attention_norm*cur cur = ggml_mul(ctx0, @@ -685,7 +691,7 @@ struct ggml_tensor * forward( // norm { // cur shape [n_embd,N,1,1] - cur = ggml_rms_norm(ctx0, inpFF); + cur = ggml_rms_norm(ctx0, inpFF, rms_norm_eps); // cur = ffn_norm*cur // cur shape [n_embd,N,1,1] @@ -729,7 +735,7 @@ struct ggml_tensor * forward( { // inpL shape [n_embd,N,1,1] - inpL = ggml_rms_norm(ctx0, inpL); + inpL = ggml_rms_norm(ctx0, inpL, rms_norm_eps); // inpL = norm*inpL // inpL shape [n_embd,N,1,1] @@ -817,7 +823,7 @@ struct ggml_tensor * forward_batch( // norm { // cur shape [n_embd,N*n_batch,1,1] - cur = ggml_rms_norm(ctx0, inpL); + cur = ggml_rms_norm(ctx0, inpL, rms_norm_eps); assert_shape_2d(cur, n_embd, N*n_batch); // cur = attention_norm*cur @@ -981,7 +987,7 @@ struct ggml_tensor * forward_batch( // norm { // cur shape [n_embd,N*n_batch,1,1] - cur = ggml_rms_norm(ctx0, inpFF); + cur = ggml_rms_norm(ctx0, inpFF, rms_norm_eps); assert_shape_2d(cur, n_embd, N*n_batch); // cur = ffn_norm*cur @@ -1034,7 +1040,7 @@ struct ggml_tensor * forward_batch( { // inpL shape [n_embd,N*n_batch,1,1] - inpL = ggml_rms_norm(ctx0, inpL); + inpL = ggml_rms_norm(ctx0, inpL, rms_norm_eps); assert_shape_2d(inpL, n_embd, N*n_batch); // inpL = norm*inpL @@ -1104,7 +1110,7 @@ struct ggml_tensor * forward_lora( // norm { // cur shape [n_embd,N,1,1] - cur = ggml_rms_norm(ctx0, inpL); + cur = ggml_rms_norm(ctx0, inpL, rms_norm_eps); // cur = attention_norm*cur cur = ggml_mul(ctx0, @@ -1251,7 +1257,7 @@ struct ggml_tensor * forward_lora( // norm { // cur shape [n_embd,N,1,1] - cur = ggml_rms_norm(ctx0, inpFF); + cur = ggml_rms_norm(ctx0, inpFF, rms_norm_eps); // cur = ffn_norm*cur // cur shape [n_embd,N,1,1] @@ -1295,7 +1301,7 @@ struct ggml_tensor * forward_lora( { // inpL shape [n_embd,N,1,1] - inpL = ggml_rms_norm(ctx0, inpL); + inpL = ggml_rms_norm(ctx0, inpL, rms_norm_eps); // inpL = norm*inpL // inpL shape [n_embd,N,1,1] |