clean up the notebook

example-fineweb.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 3,
    "id": "5a1b6d40-c917-4f30-adf3-c79a50cbc1be",
    "metadata": {},
    "outputs": [],
@@ -14,7 +14,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "id": "4552c1ab-b20f-48fc-aa4d-3bf1576261ec",
    "metadata": {},
    "outputs": [],
@@ -30,7 +30,7 @@
     "\n",
     "from trainer.SFTTrainer import train\n",
     "from model.args import MOEModelArgs\n",
-    "from model.KANamav5 import KANamav5\n",
+    "from model.KANaMoEv1 import KANaMoEv1\n",
     "\n",
     "from utils import load_model, quick_inference\n",
     "\n",
@@ -39,7 +39,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "id": "77e0b467-149e-4247-bcf6-792ee89fba9f",
    "metadata": {},
    "outputs": [],
@@ -65,18 +65,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "id": "2a900a88-b089-4089-beaa-474641957678",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[LOADING TOKENIZER]\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "tokenizer = AutoTokenizer.from_pretrained(\"Qwen/Qwen2.5-7B\")\n",
     "print(\"[TOKENIZER LOADED]\")\n",
@@ -103,51 +95,7 @@
    "execution_count": null,
    "id": "8d4fab82-866a-426e-91dc-5d424e5dc491",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "e09ca08e820741309f9c0792a4a7c96b",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Resolving data files:   0%|          | 0/23781 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "946050163a5d4e569072ef57ff221ae9",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Resolving data files:   0%|          | 0/250 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "Processing dataset:\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Tokenizing dataset: 1103585it [1:02:45, 329.69it/s]"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "# Load the dataset (replace the old one)\n",
     "# use the new dataset \"sample-10BT\" (adjust as needed)\n",
@@ -246,7 +194,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.10.15"
   }
  },
  "nbformat": 4,