Use wget for model downloads instead of llama-cli

Since we disabled CURL support (-DLLAMA_CURL=OFF), llama-cli cannot
download models from HuggingFace. Switch to using wget directly to
download the TinyLlama model, following the same pattern used in
build.yml workflow.

Fixes: Model download failures in performance-cpu and performance-metal jobs
Co-Authored-By: Alex Peng <[email protected]>

Author: devin-ai-integration[bot]

.github/workflows/performance-regression.yml

@@ -83,10 +83,8 @@ jobs:
           mkdir -p models
           # Download TinyLlama test model if not present
           if [ ! -f models/tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf ]; then
-            ./build/bin/llama-cli --hf-repo TinyLlama/TinyLlama-1.1B-Chat-v1.0 \
-              --hf-file tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf \
-              --model-download-only
-            mv ~/.cache/llama.cpp/*/tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf models/
+            wget -q --show-progress -O models/tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf \
+              https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf
           fi
 
       - name: Restore baseline database
@@ -219,10 +217,8 @@ jobs:
         run: |
           mkdir -p models
           if [ ! -f models/tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf ]; then
-            ./build/bin/llama-cli --hf-repo TinyLlama/TinyLlama-1.1B-Chat-v1.0 \
-              --hf-file tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf \
-              --model-download-only
-            mv ~/.cache/llama.cpp/*/tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf models/
+            wget -q --show-progress -O models/tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf \
+              https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf
           fi
 
       - name: Restore baseline database
@@ -353,11 +349,8 @@ jobs:
         run: |
           mkdir -p models
           if [ ! -f models/tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf ]; then
-            ./build/bin/llama-cli --hf-repo TinyLlama/TinyLlama-1.1B-Chat-v1.0 \
-              --hf-file tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf \
-              --model-download-only
-            mv ~/.cache/llama.cpp/*/tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf models/ || \
-            mv ~/Library/Caches/llama.cpp/*/tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf models/
+            wget -q --show-progress -O models/tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf \
+              https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf
           fi
 
       - name: Restore baseline database