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 | ... ```
model-conversion : remove hardcoded /bin/bash shebangs [no ci] (#15765 )
2026-07-18 02:15:58 +02:00 · 2025-09-03 13:35:49 +02:00 · 2025-09-03 12:50:47 +02:00 · 2025-09-03 16:46:01 +08:00
20 changed files with 23 additions and 18 deletions
@@ -63,7 +63,7 @@ causal-verify-logits: causal-run-original-model causal-run-converted-model
 	@MODEL_PATH="$(MODEL_PATH)" ./scripts/utils/check-nmse.py -m ${MODEL_PATH}

 causal-run-original-embeddings:
-	@./scripts/causal/run-casual-gen-embeddings-org.sh
+	@./scripts/causal/run-casual-gen-embeddings-org.py

 causal-run-converted-embeddings:
 	@./scripts/causal/run-converted-model-embeddings-logits.sh
@@ -1,4 +1,4 @@
-#/bin/bash
+#!/usr/bin/env bash

 set -e

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash

 set -e

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash

 set -e

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash

 set -e

@@ -1,4 +1,4 @@
-#/bin/bash
+#!/usr/bin/env bash

 set -e

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash

 set -e

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash

 set -e

@@ -1,4 +1,6 @@

+#!/usr/bin/env bash
+
 COLLECTION_SLUG=$(python ./create_collection.py --return-slug)
 echo "Created collection: $COLLECTION_SLUG"

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 curl --request POST \
    --url http://localhost:8080/embedding \
    --header "Content-Type: application/json" \
@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash

 # First try command line argument, then environment variable, then file
 CONVERTED_MODEL="${1:-"$CONVERTED_MODEL"}"
@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash

 set -e

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash

 set -e

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash

 set -e

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash

 set -e

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash

 set -e
 #
@@ -2417,7 +2417,11 @@ static bool ggml_backend_cann_supports_op(ggml_backend_dev_t dev,
            if (mode & GGML_ROPE_TYPE_VISION) {
                return false;
            }
-
+#ifdef ASCEND_310P
+            if(!ggml_is_contiguous(op->src[0])){
+                return false;
+            }
+#endif
            return true;
        }
        case GGML_OP_UPSCALE: {
@@ -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;
@@ -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,