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

llama : recognize 1B phi models (#4847)

Browse source 
This update categorizes models with 24 layers as MODEL_1B, ensuring compatibility with different Phi model variants without impacting existing Phi-2 model functionality.
This commit is contained in:
Austin 2024-01-10 08:39:09 -05:00 • committed by GitHub
parent d34633d8db
commit 329ff61569
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
llama.cpp
View file

@ -2829,6 +2829,7 @@ static void llm_load_hparams(
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps);
switch (hparams.n_layer) {
case 24: model.type = e_model::MODEL_1B; break;
case 32: model.type = e_model::MODEL_3B; break;
default: model.type = e_model::MODEL_UNKNOWN;
}