default n_swa for phi-3

This commit is contained in:
Xuan Son Nguyen 2024-08-08 14:02:14 +02:00
parent e44a561ab0
commit fde165e968

View file

@ -4892,7 +4892,6 @@ static void llm_load_hparams(
} break;
case LLM_ARCH_PHI3:
{
ml.get_key(LLM_KV_ATTENTION_SLIDING_WINDOW, hparams.n_swa);
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
switch (hparams.n_layer) {
@ -4901,6 +4900,17 @@ static void llm_load_hparams(
case 40: model.type = e_model::MODEL_14B; break;
default: model.type = e_model::MODEL_UNKNOWN;
}
if ((hparams.n_layer == 32 || hparams.n_layer == 40)) {
if (hparams.n_ctx_train == 4096) {
// default value for Phi-3-mini-4k-instruct and Phi-3-medium-4k-instruct
hparams.n_swa = 2047;
} else if (hparams.n_ctx_train == 131072) {
// default value for Phi-3-mini-128k-instruct and Phi-3-medium-128k-instruct
hparams.n_swa = 131072;
}
}
ml.get_key(LLM_KV_ATTENTION_SLIDING_WINDOW, hparams.n_swa, false);
} break;
case LLM_ARCH_PLAMO:
{