chore: add llama 3.1 8B gguf model

extensions/inference-nitro-extension/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@janhq/inference-cortex-extension",
   "productName": "Cortex Inference Engine",
-  "version": "1.0.14",
+  "version": "1.0.15",
   "description": "This extension embeds cortex.cpp, a lightweight inference engine written in C++. See https://nitro.jan.ai.\nAdditional dependencies could be installed to run without Cuda Toolkit installation.",
   "main": "dist/index.js",
   "node": "dist/node/index.cjs.js",

extensions/inference-nitro-extension/resources/models/llama3.1-8b-instruct/model.json

@@ -0,0 +1,42 @@
+{
+  "sources": [
+    {
+      "filename": "Meta-Llama-3.1-8B-Instruct.Q4_K_M.gguf",
+      "url": "https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct.Q4_K_M.gguf"
+    }
+  ],
+  "id": "llama3.1-8b-instruct",
+  "object": "model",
+  "name": "Llama 3.1 8B Q4",
+  "version": "1.0",
+  "description": "Meta's Llama 3 excels at general usage situations, including chat, general world knowledge, and coding.",
+  "format": "gguf",
+  "settings": {
+    "ctx_len": 131072,
+    "prompt_template": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{system_message}<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
+    "llama_model_path": "Meta-Llama-3.1-8B-Instruct.Q4_K_M.gguf",
+    "ngl": 33
+  },
+  "parameters": {
+    "temperature": 0.7,
+    "top_p": 0.95,
+    "stream": true,
+    "max_tokens": 8192,
+    "stop": [
+      "<|end_of_text|>",
+      "<|eot_id|>",
+      "<|eom_id|>"
+    ],
+    "frequency_penalty": 0,
+    "presence_penalty": 0
+  },
+  "metadata": {
+    "author": "MetaAI",
+    "tags": [
+      "8B",
+      "Featured"
+    ],
+    "size": 4920000000
+  },
+  "engine": "nitro"
+}