From: Daniel Bevenius <redacted>
Date: Wed, 3 Sep 2025 11:35:49 +0000 (+0200)
Subject: llama : fix incorrect model type for  Gemma 270M (#15764)
X-Git-Tag: upstream/0.0.6527~160
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=2c8dac72eb6acd4e20c0da251535dfc46d35178b;p=pkg%2Fggml%2Fsources%2Fllama.cpp

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 | ...
```
---

diff --git a/src/llama-model.cpp b/src/llama-model.cpp
index 58a0581e..5e54ce25 100644
--- a/src/llama-model.cpp
+++ b/src/llama-model.cpp
@@ -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);
 
                 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 34: type = LLM_TYPE_4B; break;
                     case 48: type = LLM_TYPE_12B; break;
diff --git a/src/llama-model.h b/src/llama-model.h
index fa44d800..10b1767f 100644
--- a/src/llama-model.h
+++ b/src/llama-model.h
@@ -39,7 +39,6 @@ enum llm_type {
     LLM_TYPE_410M,
     LLM_TYPE_450M,
     LLM_TYPE_475M,
-    LLM_TYPE_537M,
     LLM_TYPE_558M,
     LLM_TYPE_700M,
     LLM_TYPE_770M,