From: Daniel Bevenius <redacted>
Date: Thu, 14 Aug 2025 15:56:26 +0000 (+0200)
Subject: llama : add 18-layer model type for Gemma 3-270m (#15319)
X-Git-Tag: upstream/0.0.6199~32
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=7a0de960452f9a57de7f1d167e57b6f3ee5ac1b6;p=pkg%2Fggml%2Fsources%2Fllama.cpp

llama : add 18-layer model type for Gemma 3-270m (#15319)

This commit adds support for the 18-layer model type in the Gemma3
series, which is the size of the Gemma3-270m model.

The motivation for this commit is was the only change required for
Gemma3-270m to be converted to GGUF format and used with llama.cpp.

Once the model has been converted and uploaded to Huggingface it can be
used like this:
```console
$ ./build/bin/llama-cli -hf ggml-org/gemma-3-270m-GGUF:Q8_0
```
---

diff --git a/src/llama-model.cpp b/src/llama-model.cpp
index 58ca7df7..23a26f0c 100644
--- a/src/llama-model.cpp
+++ b/src/llama-model.cpp
@@ -1095,6 +1095,7 @@ 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 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 6fcd74d5..46f7d048 100644
--- a/src/llama-model.h
+++ b/src/llama-model.h
@@ -39,6 +39,7 @@ enum llm_type {
     LLM_TYPE_410M,
     LLM_TYPE_450M,
     LLM_TYPE_475M,
+    LLM_TYPE_537M,
     LLM_TYPE_700M,
     LLM_TYPE_770M,
     LLM_TYPE_780M,