vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-04-28 03:30:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

model : Gemma4 model type detection (#22027)

Browse source 
* model : Gemma4 model type detection

* model : Gemma4 model type detection
This commit is contained in:
Eric Zhang 2026-04-17 16:07:11 +08:00 • committed by GitHub
parent 5e6c0e18b6
commit fcc7508759
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 7 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

6
src/llama-model.cpp
View file

@ -432,6 +432,7 @@ const char * llm_type_name(llm_type type) {
case LLM_TYPE_26B: return "26B";
case LLM_TYPE_27B: return "27B";
case LLM_TYPE_30B: return "30B";
case LLM_TYPE_31B: return "31B";
case LLM_TYPE_32B: return "32B";
case LLM_TYPE_34B: return "34B";
case LLM_TYPE_35B: return "35B";
@ -466,6 +467,7 @@ const char * llm_type_name(llm_type type) {
case LLM_TYPE_16B_A1B: return "16B.A1B";
case LLM_TYPE_21B_A3B: return "21B.A3B";
case LLM_TYPE_24B_A2B: return "24B.A2B";
case LLM_TYPE_26B_A4B: return "26B.A4B";
case LLM_TYPE_30B_A3B: return "30B.A3B";
case LLM_TYPE_31B_A3_5B: return "31B.A3.5B";
case LLM_TYPE_35B_A3B: return "35B.A3B";
@ -1624,8 +1626,10 @@ void llama_model::load_hparams(llama_model_loader & ml) {
ml.get_key(LLM_KV_FINAL_LOGIT_SOFTCAPPING, hparams.f_final_logit_softcapping, false);
switch (hparams.n_layer) {
case 30: type = LLM_TYPE_26B_A4B; break;
case 35: type = LLM_TYPE_E2B; break;
case 42: type = LLM_TYPE_E4B; break; // to confirm: E4B or E5B?
case 42: type = LLM_TYPE_E4B; break;
case 60: type = LLM_TYPE_31B; break;
default: type = LLM_TYPE_UNKNOWN;
}
} break;

2
src/llama-model.h
View file

@ -84,6 +84,7 @@ enum llm_type {
LLM_TYPE_26B,
LLM_TYPE_27B,
LLM_TYPE_30B,
LLM_TYPE_31B,
LLM_TYPE_32B,
LLM_TYPE_34B,
LLM_TYPE_35B,
@ -118,6 +119,7 @@ enum llm_type {
LLM_TYPE_16B_A1B,
LLM_TYPE_21B_A3B, // Ernie MoE small
LLM_TYPE_24B_A2B, // lfm2moe
LLM_TYPE_26B_A4B, // Gemma4
LLM_TYPE_30B_A3B,
LLM_TYPE_31B_A3_5B,
LLM_TYPE_35B_A3B, // Qwen3.5