add: tinyllama

models/tinyllama-1.1b/model.json

@@ -0,0 +1,34 @@
+{
+  "sources": [
+    {
+      "filename": "tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf",
+      "url": "https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf"
+    }
+  ],
+  "id": "tinyllama-1.1b",
+  "object": "model",
+  "name": "TinyLlama Chat 1.1B Q4",
+  "version": "1.0",
+  "description": "TinyLlama is a tiny model with only 1.1B. It's a good model for less powerful computers.",
+  "format": "gguf",
+  "settings": {
+    "ctx_len": 4096,
+    "prompt_template": "<|system|>\n{system_message}<|user|>\n{prompt}<|assistant|>",
+    "llama_model_path": "tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf"
+  },
+  "parameters": {
+    "temperature": 0.7,
+    "top_p": 0.95,
+    "stream": true,
+    "max_tokens": 2048,
+    "stop": [],
+    "frequency_penalty": 0,
+    "presence_penalty": 0
+  },
+  "metadata": {
+    "author": "TinyLlama",
+    "tags": ["Tiny", "Foundation Model"],
+    "size": 669000000
+  },
+  "engine": "nitro"
+}