new llama nvidia model

dev-llama-3-large.yaml

@@ -9,7 +9,7 @@ config_file: |
   f16: true 
   gpu_layers: 85
   parameters:
-    model: downloads/llama_backend/Hermes-2-Theta-Llama-3-70B-Q5_K_M.gguf
+    model: downloads/llama_backend/Llama-3.1-Nemotron-70B-Instruct-HF-Q6_K 
   
   template:
     chat_message: |
@@ -54,8 +54,9 @@ config_file: |
             "model": "dev-llama-3",
             "messages": [{"role": "user", "content": "How are you doing?", "temperature": 0.1}]
         }'
-files:
-- filename: "downloads/llama_backend/Hermes-2-Theta-Llama-3-70B-Q5_K_M.gguf"
-  sha256: ""
-  uri: "https://huggingface.co/bartowski/Hermes-2-Theta-Llama-3-70B-GGUF/resolve/main/Hermes-2-Theta-Llama-3-70B-Q5_K_M.gguf"
-         
+# files:
+# - filename: "downloads/llama_backend/Hermes-2-Theta-Llama-3-70B-Q5_K_M.gguf"
+#   sha256: ""
+#   uri: "https://huggingface.co/bartowski/Hermes-2-Theta-Llama-3-70B-GGUF/resolve/main/Hermes-2-Theta-Llama-3-70B-Q5_K_M.gguf"
+
\ No newline at end of file
+# download model with    huggingface-cli download bartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF --local-dir /data/localai-data/downloads/llama_backend  --include '*Q6_K*'