update TODO

TODO.md

@@ -1,4 +1,7 @@
 # TODO
+- [ ] proper tool calling support  
+- [ ] home assistant component text streaming support  
+- [ ] new models based on qwen3  
 - [x] support new LLM APIs  
     - rewrite how services are called  
     - handle no API selected  

train.ipynb

@@ -44,7 +44,7 @@
     "%pip install -r data/requirements.txt\n",
     "from data.generate_home_assistant_data import main as generate_data\n",
     "\n",
-    "generate_data([\"--train\", \"--test\", \"--large\", \"--sharegpt\", \"--language\", \"english\", \"german\", \"french\", \"spanish\"])"
+    "generate_data([\"--train\", \"--test\", \"--large\", \"--sharegpt\", \"--language\", \"english\", \"german\", \"french\", \"spanish\", \"polish\"])"
    ]
   },
   {
@@ -85,6 +85,34 @@
     "    save_steps=200, save_total_limit=1, eval_steps=200, logging_steps=2,\n",
     "))"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e71572c4",
+   "metadata": {},
+   "source": [
+    "# Qwen3"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fdf2b998",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "do_training_run(TrainingRunArguments(\n",
+    "    run_name=get_next_run_name(\"Home-Qwen-3-1.7B\"),\n",
+    "    base_model=\"Qwen/Qwen3-1.7B\",\n",
+    "    bf16=True,\n",
+    "    train_dataset=\"data/home_assistant_train.jsonl\",\n",
+    "    test_dataset=\"data/home_assistant_test.jsonl\",\n",
+    "    learning_rate=2e-5, learning_rate_warmup=0.03, \n",
+    "    batch_size=64, micro_batch_size=2, epochs=1,\n",
+    "    ctx_size=2048,\n",
+    "    save_steps=200, save_total_limit=1, eval_steps=200, logging_steps=2,\n",
+    "))"
+   ]
   }
  ],
  "metadata": {