happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

llama : fix incorrect model type for Gemma 270M (#15764) 

This commit fixes the model type for the Gemma 270M model in
llama_model.cpp which should be LLM_TYPE_270M. I incorrectly added this
previously as LLM_TYPE_537M which was wrong.

The motivation for this is that it causes the model to not be identified
properly when using tools like llama-bench. For example:
```console
$ ./build/bin/llama-bench -m models/gemma-3-270m-Q8_0.gguf
| model                          |       size | ...
| ------------------------------ | ---------: | ...
| gemma3 ?B Q8_0                 | 271.81 MiB | ...
| gemma3 ?B Q8_0                 | 271.81 MiB | ...
```

With the changes in this commit the output will be:
```console
$ ./build/bin/llama-bench -m models/gemma-3-270m-Q8_0.gguf
| model                          |       size | ...
| ------------------------------ | ---------: | ...
| gemma3 270M Q8_0               | 271.81 MiB | ...
| gemma3 270M Q8_0               | 271.81 MiB | ...
```
This commit is contained in:
Daniel Bevenius 2025-09-03 13:35:49 +02:00 committed by GitHub
parent 40a751ea9a
commit 2c8dac72eb
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 1 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama-model.cpp
View File

@ -1110,7 +1110,7 @@ void llama_model::load_hparams(llama_model_loader & ml) {
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
switch (hparams.n_layer) { switch (hparams.n_layer) {
case 18: type = LLM_TYPE_537M; break; case 18: type = LLM_TYPE_270M; break;
case 26: type = LLM_TYPE_1B; break; case 26: type = LLM_TYPE_1B; break;
case 34: type = LLM_TYPE_4B; break; case 34: type = LLM_TYPE_4B; break;
case 48: type = LLM_TYPE_12B; break; case 48: type = LLM_TYPE_12B; break;

1
src/llama-model.h
View File

@ -39,7 +39,6 @@ enum llm_type {
LLM_TYPE_410M, LLM_TYPE_410M,
LLM_TYPE_450M, LLM_TYPE_450M,
LLM_TYPE_475M, LLM_TYPE_475M,
LLM_TYPE_537M,
LLM_TYPE_558M, LLM_TYPE_558M,
LLM_TYPE_700M, LLM_TYPE_700M,
LLM_TYPE_770M, LLM_TYPE_770M,