Updated notebooks wip

sia/llm_engine/qwq_llm_engine.ipynb

@@ -57,7 +57,6 @@
     "    load_in_4bit = True, # False for LoRA 16bit\n",
     "    fast_inference = True, # Enable vLLM fast inference\n",
     "    gpu_memory_utilization = 0.8, # Reduce if out of memory\n",
-    "    tokenizer = tokenizer,\n",
     ")"
    ]
   },
@@ -175,19 +174,7 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "ename": "",
-     "evalue": "",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[1;31mThe Kernel crashed while executing code in the current cell or a previous cell. \n",
-      "\u001b[1;31mPlease review the code in the cell(s) to identify a possible cause of the failure. \n",
-      "\u001b[1;31mClick <a href='https://aka.ms/vscodeJupyterKernelCrash'>here</a> for more info. \n",
-      "\u001b[1;31mView Jupyter <a href='command:jupyter.viewOutput'>log</a> for further details."
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "\n",
     "generation_thread.join()"
@@ -198,7 +185,7 @@
   "kernelspec": {
    "display_name": "sia",
    "language": "python",
-   "name": "python3"
+   "name": "sia"
   },
   "language_info": {
    "codemirror_mode": {