Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-26 14:20:31 +01:00
Code Issues Packages Projects Releases Wiki Activity

llama : fix Qwen model type strings

Browse Source
This commit is contained in:
Georgi Gerganov 2024-11-09 11:26:34 +02:00
parent 46323fa9ef
commit f018acba22
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/llama.cpp
View File

@ -2301,6 +2301,7 @@ enum e_model {
MODEL_1B,
MODEL_1_3B,
MODEL_1_4B,
MODEL_1_5B,
MODEL_1_6B,
MODEL_2B,
MODEL_2_8B,
@ -5227,6 +5228,7 @@ static const char * llama_model_type_name(e_model type) {
case MODEL_1B: return "1B";
case MODEL_1_3B: return "1.3B";
case MODEL_1_4B: return "1.4B";
case MODEL_1_5B: return "1.5B";
case MODEL_1_6B: return "1.6B";
case MODEL_2B: return "2B";
case MODEL_2_8B: return "2.8B";
@ -5598,6 +5600,7 @@ static void llm_load_hparams(
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
switch (hparams.n_layer) {
case 24: model.type = hparams.n_embd == 1024 ? e_model::MODEL_0_5B : e_model::MODEL_1B; break;
case 28: model.type = hparams.n_embd == 1536 ? e_model::MODEL_1_5B : e_model::MODEL_7B; break;
case 32: model.type = e_model::MODEL_7B; break;
case 40: model.type = hparams.n_head() == 20 ? e_model::MODEL_4B : e_model::MODEL_13B; break;
case 80: model.type = e_model::MODEL_70B; break;