Delete Untitled.ipynb

Untitled.ipynb

@@ -1,178 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "1450e971-02a8-456f-927d-6a7cd1237fb0",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "import torch"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "ac7202ad-16e2-4b5c-b622-3b459d537844",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "a = torch.load(\"pytorch_model.bin\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "2f0a9726-609a-40ab-96ea-ebc783d2bd6d",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "dict_keys(['language_model.model.tok_embeddings.weight', 'language_model.model.layers.0.attention.wqkv.weight', 'language_model.model.layers.0.attention.wo.weight', 'language_model.model.layers.0.feed_forward.w1.weight', 'language_model.model.layers.0.feed_forward.w3.weight', 'language_model.model.layers.0.feed_forward.w2.weight', 'language_model.model.layers.0.attention_norm.weight', 'language_model.model.layers.0.ffn_norm.weight', 'language_model.model.layers.1.attention.wqkv.weight', 'language_model.model.layers.1.attention.wo.weight', 'language_model.model.layers.1.feed_forward.w1.weight', 'language_model.model.layers.1.feed_forward.w3.weight', 'language_model.model.layers.1.feed_forward.w2.weight', 'language_model.model.layers.1.attention_norm.weight', 'language_model.model.layers.1.ffn_norm.weight', 'language_model.model.layers.2.attention.wqkv.weight', 'language_model.model.layers.2.attention.wo.weight', 'language_model.model.layers.2.feed_forward.w1.weight', 'language_model.model.layers.2.feed_forward.w3.weight', 'language_model.model.layers.2.feed_forward.w2.weight', 'language_model.model.layers.2.attention_norm.weight', 'language_model.model.layers.2.ffn_norm.weight', 'language_model.model.layers.3.attention.wqkv.weight', 'language_model.model.layers.3.attention.wo.weight', 'language_model.model.layers.3.feed_forward.w1.weight', 'language_model.model.layers.3.feed_forward.w3.weight', 'language_model.model.layers.3.feed_forward.w2.weight', 'language_model.model.layers.3.attention_norm.weight', 'language_model.model.layers.3.ffn_norm.weight', 'language_model.model.layers.4.attention.wqkv.weight', 'language_model.model.layers.4.attention.wo.weight', 'language_model.model.layers.4.feed_forward.w1.weight', 'language_model.model.layers.4.feed_forward.w3.weight', 'language_model.model.layers.4.feed_forward.w2.weight', 'language_model.model.layers.4.attention_norm.weight', 'language_model.model.layers.4.ffn_norm.weight', 'language_model.model.layers.5.attention.wqkv.weight', 'language_model.model.layers.5.attention.wo.weight', 'language_model.model.layers.5.feed_forward.w1.weight', 'language_model.model.layers.5.feed_forward.w3.weight', 'language_model.model.layers.5.feed_forward.w2.weight', 'language_model.model.layers.5.attention_norm.weight', 'language_model.model.layers.5.ffn_norm.weight', 'language_model.model.layers.6.attention.wqkv.weight', 'language_model.model.layers.6.attention.wo.weight', 'language_model.model.layers.6.feed_forward.w1.weight', 'language_model.model.layers.6.feed_forward.w3.weight', 'language_model.model.layers.6.feed_forward.w2.weight', 'language_model.model.layers.6.attention_norm.weight', 'language_model.model.layers.6.ffn_norm.weight', 'language_model.model.layers.7.attention.wqkv.weight', 'language_model.model.layers.7.attention.wo.weight', 'language_model.model.layers.7.feed_forward.w1.weight', 'language_model.model.layers.7.feed_forward.w3.weight', 'language_model.model.layers.7.feed_forward.w2.weight', 'language_model.model.layers.7.attention_norm.weight', 'language_model.model.layers.7.ffn_norm.weight', 'language_model.model.layers.8.attention.wqkv.weight', 'language_model.model.layers.8.attention.wo.weight', 'language_model.model.layers.8.feed_forward.w1.weight', 'language_model.model.layers.8.feed_forward.w3.weight', 'language_model.model.layers.8.feed_forward.w2.weight', 'language_model.model.layers.8.attention_norm.weight', 'language_model.model.layers.8.ffn_norm.weight', 'language_model.model.layers.9.attention.wqkv.weight', 'language_model.model.layers.9.attention.wo.weight', 'language_model.model.layers.9.feed_forward.w1.weight', 'language_model.model.layers.9.feed_forward.w3.weight', 'language_model.model.layers.9.feed_forward.w2.weight', 'language_model.model.layers.9.attention_norm.weight', 'language_model.model.layers.9.ffn_norm.weight', 'language_model.model.layers.10.attention.wqkv.weight', 'language_model.model.layers.10.attention.wo.weight', 'language_model.model.layers.10.feed_forward.w1.weight', 'language_model.model.layers.10.feed_forward.w3.weight', 'language_model.model.layers.10.feed_forward.w2.weight', 'language_model.model.layers.10.attention_norm.weight', 'language_model.model.layers.10.ffn_norm.weight', 'language_model.model.layers.11.attention.wqkv.weight', 'language_model.model.layers.11.attention.wo.weight', 'language_model.model.layers.11.feed_forward.w1.weight', 'language_model.model.layers.11.feed_forward.w3.weight', 'language_model.model.layers.11.feed_forward.w2.weight', 'language_model.model.layers.11.attention_norm.weight', 'language_model.model.layers.11.ffn_norm.weight', 'language_model.model.layers.12.attention.wqkv.weight', 'language_model.model.layers.12.attention.wo.weight', 'language_model.model.layers.12.feed_forward.w1.weight', 'language_model.model.layers.12.feed_forward.w3.weight', 'language_model.model.layers.12.feed_forward.w2.weight', 'language_model.model.layers.12.attention_norm.weight', 'language_model.model.layers.12.ffn_norm.weight', 'language_model.model.layers.13.attention.wqkv.weight', 'language_model.model.layers.13.attention.wo.weight', 'language_model.model.layers.13.feed_forward.w1.weight', 'language_model.model.layers.13.feed_forward.w3.weight', 'language_model.model.layers.13.feed_forward.w2.weight', 'language_model.model.layers.13.attention_norm.weight', 'language_model.model.layers.13.ffn_norm.weight', 'language_model.model.layers.14.attention.wqkv.weight', 'language_model.model.layers.14.attention.wo.weight', 'language_model.model.layers.14.feed_forward.w1.weight', 'language_model.model.layers.14.feed_forward.w3.weight', 'language_model.model.layers.14.feed_forward.w2.weight', 'language_model.model.layers.14.attention_norm.weight', 'language_model.model.layers.14.ffn_norm.weight', 'language_model.model.layers.15.attention.wqkv.weight', 'language_model.model.layers.15.attention.wo.weight', 'language_model.model.layers.15.feed_forward.w1.weight', 'language_model.model.layers.15.feed_forward.w3.weight', 'language_model.model.layers.15.feed_forward.w2.weight', 'language_model.model.layers.15.attention_norm.weight', 'language_model.model.layers.15.ffn_norm.weight', 'language_model.model.layers.16.attention.wqkv.weight', 'language_model.model.layers.16.attention.wo.weight', 'language_model.model.layers.16.feed_forward.w1.weight', 'language_model.model.layers.16.feed_forward.w3.weight', 'language_model.model.layers.16.feed_forward.w2.weight', 'language_model.model.layers.16.attention_norm.weight', 'language_model.model.layers.16.ffn_norm.weight', 'language_model.model.layers.17.attention.wqkv.weight', 'language_model.model.layers.17.attention.wo.weight', 'language_model.model.layers.17.feed_forward.w1.weight', 'language_model.model.layers.17.feed_forward.w3.weight', 'language_model.model.layers.17.feed_forward.w2.weight', 'language_model.model.layers.17.attention_norm.weight', 'language_model.model.layers.17.ffn_norm.weight', 'language_model.model.layers.18.attention.wqkv.weight', 'language_model.model.layers.18.attention.wo.weight', 'language_model.model.layers.18.feed_forward.w1.weight', 'language_model.model.layers.18.feed_forward.w3.weight', 'language_model.model.layers.18.feed_forward.w2.weight', 'language_model.model.layers.18.attention_norm.weight', 'language_model.model.layers.18.ffn_norm.weight', 'language_model.model.layers.19.attention.wqkv.weight', 'language_model.model.layers.19.attention.wo.weight', 'language_model.model.layers.19.feed_forward.w1.weight', 'language_model.model.layers.19.feed_forward.w3.weight', 'language_model.model.layers.19.feed_forward.w2.weight', 'language_model.model.layers.19.attention_norm.weight', 'language_model.model.layers.19.ffn_norm.weight', 'language_model.model.layers.20.attention.wqkv.weight', 'language_model.model.layers.20.attention.wo.weight', 'language_model.model.layers.20.feed_forward.w1.weight', 'language_model.model.layers.20.feed_forward.w3.weight', 'language_model.model.layers.20.feed_forward.w2.weight', 'language_model.model.layers.20.attention_norm.weight', 'language_model.model.layers.20.ffn_norm.weight', 'language_model.model.layers.21.attention.wqkv.weight', 'language_model.model.layers.21.attention.wo.weight', 'language_model.model.layers.21.feed_forward.w1.weight', 'language_model.model.layers.21.feed_forward.w3.weight', 'language_model.model.layers.21.feed_forward.w2.weight', 'language_model.model.layers.21.attention_norm.weight', 'language_model.model.layers.21.ffn_norm.weight', 'language_model.model.layers.22.attention.wqkv.weight', 'language_model.model.layers.22.attention.wo.weight', 'language_model.model.layers.22.feed_forward.w1.weight', 'language_model.model.layers.22.feed_forward.w3.weight', 'language_model.model.layers.22.feed_forward.w2.weight', 'language_model.model.layers.22.attention_norm.weight', 'language_model.model.layers.22.ffn_norm.weight', 'language_model.model.layers.23.attention.wqkv.weight', 'language_model.model.layers.23.attention.wo.weight', 'language_model.model.layers.23.feed_forward.w1.weight', 'language_model.model.layers.23.feed_forward.w3.weight', 'language_model.model.layers.23.feed_forward.w2.weight', 'language_model.model.layers.23.attention_norm.weight', 'language_model.model.layers.23.ffn_norm.weight', 'language_model.model.layers.24.attention.wqkv.weight', 'language_model.model.layers.24.attention.wo.weight', 'language_model.model.layers.24.feed_forward.w1.weight', 'language_model.model.layers.24.feed_forward.w3.weight', 'language_model.model.layers.24.feed_forward.w2.weight', 'language_model.model.layers.24.attention_norm.weight', 'language_model.model.layers.24.ffn_norm.weight', 'language_model.model.layers.25.attention.wqkv.weight', 'language_model.model.layers.25.attention.wo.weight', 'language_model.model.layers.25.feed_forward.w1.weight', 'language_model.model.layers.25.feed_forward.w3.weight', 'language_model.model.layers.25.feed_forward.w2.weight', 'language_model.model.layers.25.attention_norm.weight', 'language_model.model.layers.25.ffn_norm.weight', 'language_model.model.layers.26.attention.wqkv.weight', 'language_model.model.layers.26.attention.wo.weight', 'language_model.model.layers.26.feed_forward.w1.weight', 'language_model.model.layers.26.feed_forward.w3.weight', 'language_model.model.layers.26.feed_forward.w2.weight', 'language_model.model.layers.26.attention_norm.weight', 'language_model.model.layers.26.ffn_norm.weight', 'language_model.model.layers.27.attention.wqkv.weight', 'language_model.model.layers.27.attention.wo.weight', 'language_model.model.layers.27.feed_forward.w1.weight', 'language_model.model.layers.27.feed_forward.w3.weight', 'language_model.model.layers.27.feed_forward.w2.weight', 'language_model.model.layers.27.attention_norm.weight', 'language_model.model.layers.27.ffn_norm.weight', 'language_model.model.layers.28.attention.wqkv.weight', 'language_model.model.layers.28.attention.wo.weight', 'language_model.model.layers.28.feed_forward.w1.weight', 'language_model.model.layers.28.feed_forward.w3.weight', 'language_model.model.layers.28.feed_forward.w2.weight', 'language_model.model.layers.28.attention_norm.weight', 'language_model.model.layers.28.ffn_norm.weight', 'language_model.model.layers.29.attention.wqkv.weight', 'language_model.model.layers.29.attention.wo.weight', 'language_model.model.layers.29.feed_forward.w1.weight', 'language_model.model.layers.29.feed_forward.w3.weight', 'language_model.model.layers.29.feed_forward.w2.weight', 'language_model.model.layers.29.attention_norm.weight', 'language_model.model.layers.29.ffn_norm.weight', 'language_model.model.layers.30.attention.wqkv.weight', 'language_model.model.layers.30.attention.wo.weight', 'language_model.model.layers.30.feed_forward.w1.weight', 'language_model.model.layers.30.feed_forward.w3.weight', 'language_model.model.layers.30.feed_forward.w2.weight', 'language_model.model.layers.30.attention_norm.weight', 'language_model.model.layers.30.ffn_norm.weight', 'language_model.model.layers.31.attention.wqkv.weight', 'language_model.model.layers.31.attention.wo.weight', 'language_model.model.layers.31.feed_forward.w1.weight', 'language_model.model.layers.31.feed_forward.w3.weight', 'language_model.model.layers.31.feed_forward.w2.weight', 'language_model.model.layers.31.attention_norm.weight', 'language_model.model.layers.31.ffn_norm.weight', 'language_model.model.layers.32.attention.wqkv.weight', 'language_model.model.layers.32.attention.wo.weight', 'language_model.model.layers.32.feed_forward.w1.weight', 'language_model.model.layers.32.feed_forward.w3.weight', 'language_model.model.layers.32.feed_forward.w2.weight', 'language_model.model.layers.32.attention_norm.weight', 'language_model.model.layers.32.ffn_norm.weight', 'language_model.model.layers.33.attention.wqkv.weight', 'language_model.model.layers.33.attention.wo.weight', 'language_model.model.layers.33.feed_forward.w1.weight', 'language_model.model.layers.33.feed_forward.w3.weight', 'language_model.model.layers.33.feed_forward.w2.weight', 'language_model.model.layers.33.attention_norm.weight', 'language_model.model.layers.33.ffn_norm.weight', 'language_model.model.layers.34.attention.wqkv.weight', 'language_model.model.layers.34.attention.wo.weight', 'language_model.model.layers.34.feed_forward.w1.weight', 'language_model.model.layers.34.feed_forward.w3.weight', 'language_model.model.layers.34.feed_forward.w2.weight', 'language_model.model.layers.34.attention_norm.weight', 'language_model.model.layers.34.ffn_norm.weight', 'language_model.model.layers.35.attention.wqkv.weight', 'language_model.model.layers.35.attention.wo.weight', 'language_model.model.layers.35.feed_forward.w1.weight', 'language_model.model.layers.35.feed_forward.w3.weight', 'language_model.model.layers.35.feed_forward.w2.weight', 'language_model.model.layers.35.attention_norm.weight', 'language_model.model.layers.35.ffn_norm.weight', 'language_model.model.layers.36.attention.wqkv.weight', 'language_model.model.layers.36.attention.wo.weight', 'language_model.model.layers.36.feed_forward.w1.weight', 'language_model.model.layers.36.feed_forward.w3.weight', 'language_model.model.layers.36.feed_forward.w2.weight', 'language_model.model.layers.36.attention_norm.weight', 'language_model.model.layers.36.ffn_norm.weight', 'language_model.model.layers.37.attention.wqkv.weight', 'language_model.model.layers.37.attention.wo.weight', 'language_model.model.layers.37.feed_forward.w1.weight', 'language_model.model.layers.37.feed_forward.w3.weight', 'language_model.model.layers.37.feed_forward.w2.weight', 'language_model.model.layers.37.attention_norm.weight', 'language_model.model.layers.37.ffn_norm.weight', 'language_model.model.layers.38.attention.wqkv.weight', 'language_model.model.layers.38.attention.wo.weight', 'language_model.model.layers.38.feed_forward.w1.weight', 'language_model.model.layers.38.feed_forward.w3.weight', 'language_model.model.layers.38.feed_forward.w2.weight', 'language_model.model.layers.38.attention_norm.weight', 'language_model.model.layers.38.ffn_norm.weight', 'language_model.model.layers.39.attention.wqkv.weight', 'language_model.model.layers.39.attention.wo.weight', 'language_model.model.layers.39.feed_forward.w1.weight', 'language_model.model.layers.39.feed_forward.w3.weight', 'language_model.model.layers.39.feed_forward.w2.weight', 'language_model.model.layers.39.attention_norm.weight', 'language_model.model.layers.39.ffn_norm.weight', 'language_model.model.layers.40.attention.wqkv.weight', 'language_model.model.layers.40.attention.wo.weight', 'language_model.model.layers.40.feed_forward.w1.weight', 'language_model.model.layers.40.feed_forward.w3.weight', 'language_model.model.layers.40.feed_forward.w2.weight', 'language_model.model.layers.40.attention_norm.weight', 'language_model.model.layers.40.ffn_norm.weight', 'language_model.model.layers.41.attention.wqkv.weight', 'language_model.model.layers.41.attention.wo.weight', 'language_model.model.layers.41.feed_forward.w1.weight', 'language_model.model.layers.41.feed_forward.w3.weight', 'language_model.model.layers.41.feed_forward.w2.weight', 'language_model.model.layers.41.attention_norm.weight', 'language_model.model.layers.41.ffn_norm.weight', 'language_model.model.layers.42.attention.wqkv.weight', 'language_model.model.layers.42.attention.wo.weight', 'language_model.model.layers.42.feed_forward.w1.weight', 'language_model.model.layers.42.feed_forward.w3.weight', 'language_model.model.layers.42.feed_forward.w2.weight', 'language_model.model.layers.42.attention_norm.weight', 'language_model.model.layers.42.ffn_norm.weight', 'language_model.model.layers.43.attention.wqkv.weight', 'language_model.model.layers.43.attention.wo.weight', 'language_model.model.layers.43.feed_forward.w1.weight', 'language_model.model.layers.43.feed_forward.w3.weight', 'language_model.model.layers.43.feed_forward.w2.weight', 'language_model.model.layers.43.attention_norm.weight', 'language_model.model.layers.43.ffn_norm.weight', 'language_model.model.layers.44.attention.wqkv.weight', 'language_model.model.layers.44.attention.wo.weight', 'language_model.model.layers.44.feed_forward.w1.weight', 'language_model.model.layers.44.feed_forward.w3.weight', 'language_model.model.layers.44.feed_forward.w2.weight', 'language_model.model.layers.44.attention_norm.weight', 'language_model.model.layers.44.ffn_norm.weight', 'language_model.model.layers.45.attention.wqkv.weight', 'language_model.model.layers.45.attention.wo.weight', 'language_model.model.layers.45.feed_forward.w1.weight', 'language_model.model.layers.45.feed_forward.w3.weight', 'language_model.model.layers.45.feed_forward.w2.weight', 'language_model.model.layers.45.attention_norm.weight', 'language_model.model.layers.45.ffn_norm.weight', 'language_model.model.layers.46.attention.wqkv.weight', 'language_model.model.layers.46.attention.wo.weight', 'language_model.model.layers.46.feed_forward.w1.weight', 'language_model.model.layers.46.feed_forward.w3.weight', 'language_model.model.layers.46.feed_forward.w2.weight', 'language_model.model.layers.46.attention_norm.weight', 'language_model.model.layers.46.ffn_norm.weight', 'language_model.model.layers.47.attention.wqkv.weight', 'language_model.model.layers.47.attention.wo.weight', 'language_model.model.layers.47.feed_forward.w1.weight', 'language_model.model.layers.47.feed_forward.w3.weight', 'language_model.model.layers.47.feed_forward.w2.weight', 'language_model.model.layers.47.attention_norm.weight', 'language_model.model.layers.47.ffn_norm.weight', 'language_model.model.norm.weight', 'language_model.output.weight'])"
-      ]
-     },
-     "execution_count": 16,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "a.keys()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 24,
-   "id": "297b187d-3e32-4422-bdad-5963d35b442b",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "dict_keys(['model.tok_embeddings.weight', 'model.layers.0.attention.wqkv.weight', 'model.layers.0.attention.wo.weight', 'model.layers.0.feed_forward.w1.weight', 'model.layers.0.feed_forward.w3.weight', 'model.layers.0.feed_forward.w2.weight', 'model.layers.0.attention_norm.weight', 'model.layers.0.ffn_norm.weight', 'model.layers.1.attention.wqkv.weight', 'model.layers.1.attention.wo.weight', 'model.layers.1.feed_forward.w1.weight', 'model.layers.1.feed_forward.w3.weight', 'model.layers.1.feed_forward.w2.weight', 'model.layers.1.attention_norm.weight', 'model.layers.1.ffn_norm.weight', 'model.layers.2.attention.wqkv.weight', 'model.layers.2.attention.wo.weight', 'model.layers.2.feed_forward.w1.weight', 'model.layers.2.feed_forward.w3.weight', 'model.layers.2.feed_forward.w2.weight', 'model.layers.2.attention_norm.weight', 'model.layers.2.ffn_norm.weight', 'model.layers.3.attention.wqkv.weight', 'model.layers.3.attention.wo.weight', 'model.layers.3.feed_forward.w1.weight', 'model.layers.3.feed_forward.w3.weight', 'model.layers.3.feed_forward.w2.weight', 'model.layers.3.attention_norm.weight', 'model.layers.3.ffn_norm.weight', 'model.layers.4.attention.wqkv.weight', 'model.layers.4.attention.wo.weight', 'model.layers.4.feed_forward.w1.weight', 'model.layers.4.feed_forward.w3.weight', 'model.layers.4.feed_forward.w2.weight', 'model.layers.4.attention_norm.weight', 'model.layers.4.ffn_norm.weight', 'model.layers.5.attention.wqkv.weight', 'model.layers.5.attention.wo.weight', 'model.layers.5.feed_forward.w1.weight', 'model.layers.5.feed_forward.w3.weight', 'model.layers.5.feed_forward.w2.weight', 'model.layers.5.attention_norm.weight', 'model.layers.5.ffn_norm.weight', 'model.layers.6.attention.wqkv.weight', 'model.layers.6.attention.wo.weight', 'model.layers.6.feed_forward.w1.weight', 'model.layers.6.feed_forward.w3.weight', 'model.layers.6.feed_forward.w2.weight', 'model.layers.6.attention_norm.weight', 'model.layers.6.ffn_norm.weight', 'model.layers.7.attention.wqkv.weight', 'model.layers.7.attention.wo.weight', 'model.layers.7.feed_forward.w1.weight', 'model.layers.7.feed_forward.w3.weight', 'model.layers.7.feed_forward.w2.weight', 'model.layers.7.attention_norm.weight', 'model.layers.7.ffn_norm.weight', 'model.layers.8.attention.wqkv.weight', 'model.layers.8.attention.wo.weight', 'model.layers.8.feed_forward.w1.weight', 'model.layers.8.feed_forward.w3.weight', 'model.layers.8.feed_forward.w2.weight', 'model.layers.8.attention_norm.weight', 'model.layers.8.ffn_norm.weight', 'model.layers.9.attention.wqkv.weight', 'model.layers.9.attention.wo.weight', 'model.layers.9.feed_forward.w1.weight', 'model.layers.9.feed_forward.w3.weight', 'model.layers.9.feed_forward.w2.weight', 'model.layers.9.attention_norm.weight', 'model.layers.9.ffn_norm.weight', 'model.layers.10.attention.wqkv.weight', 'model.layers.10.attention.wo.weight', 'model.layers.10.feed_forward.w1.weight', 'model.layers.10.feed_forward.w3.weight', 'model.layers.10.feed_forward.w2.weight', 'model.layers.10.attention_norm.weight', 'model.layers.10.ffn_norm.weight', 'model.layers.11.attention.wqkv.weight', 'model.layers.11.attention.wo.weight', 'model.layers.11.feed_forward.w1.weight', 'model.layers.11.feed_forward.w3.weight', 'model.layers.11.feed_forward.w2.weight', 'model.layers.11.attention_norm.weight', 'model.layers.11.ffn_norm.weight', 'model.layers.12.attention.wqkv.weight', 'model.layers.12.attention.wo.weight', 'model.layers.12.feed_forward.w1.weight', 'model.layers.12.feed_forward.w3.weight', 'model.layers.12.feed_forward.w2.weight', 'model.layers.12.attention_norm.weight', 'model.layers.12.ffn_norm.weight', 'model.layers.13.attention.wqkv.weight', 'model.layers.13.attention.wo.weight', 'model.layers.13.feed_forward.w1.weight', 'model.layers.13.feed_forward.w3.weight', 'model.layers.13.feed_forward.w2.weight', 'model.layers.13.attention_norm.weight', 'model.layers.13.ffn_norm.weight', 'model.layers.14.attention.wqkv.weight', 'model.layers.14.attention.wo.weight', 'model.layers.14.feed_forward.w1.weight', 'model.layers.14.feed_forward.w3.weight', 'model.layers.14.feed_forward.w2.weight', 'model.layers.14.attention_norm.weight', 'model.layers.14.ffn_norm.weight', 'model.layers.15.attention.wqkv.weight', 'model.layers.15.attention.wo.weight', 'model.layers.15.feed_forward.w1.weight', 'model.layers.15.feed_forward.w3.weight', 'model.layers.15.feed_forward.w2.weight', 'model.layers.15.attention_norm.weight', 'model.layers.15.ffn_norm.weight', 'model.layers.16.attention.wqkv.weight', 'model.layers.16.attention.wo.weight', 'model.layers.16.feed_forward.w1.weight', 'model.layers.16.feed_forward.w3.weight', 'model.layers.16.feed_forward.w2.weight', 'model.layers.16.attention_norm.weight', 'model.layers.16.ffn_norm.weight', 'model.layers.17.attention.wqkv.weight', 'model.layers.17.attention.wo.weight', 'model.layers.17.feed_forward.w1.weight', 'model.layers.17.feed_forward.w3.weight', 'model.layers.17.feed_forward.w2.weight', 'model.layers.17.attention_norm.weight', 'model.layers.17.ffn_norm.weight', 'model.layers.18.attention.wqkv.weight', 'model.layers.18.attention.wo.weight', 'model.layers.18.feed_forward.w1.weight', 'model.layers.18.feed_forward.w3.weight', 'model.layers.18.feed_forward.w2.weight', 'model.layers.18.attention_norm.weight', 'model.layers.18.ffn_norm.weight', 'model.layers.19.attention.wqkv.weight', 'model.layers.19.attention.wo.weight', 'model.layers.19.feed_forward.w1.weight', 'model.layers.19.feed_forward.w3.weight', 'model.layers.19.feed_forward.w2.weight', 'model.layers.19.attention_norm.weight', 'model.layers.19.ffn_norm.weight', 'model.layers.20.attention.wqkv.weight', 'model.layers.20.attention.wo.weight', 'model.layers.20.feed_forward.w1.weight', 'model.layers.20.feed_forward.w3.weight', 'model.layers.20.feed_forward.w2.weight', 'model.layers.20.attention_norm.weight', 'model.layers.20.ffn_norm.weight', 'model.layers.21.attention.wqkv.weight', 'model.layers.21.attention.wo.weight', 'model.layers.21.feed_forward.w1.weight', 'model.layers.21.feed_forward.w3.weight', 'model.layers.21.feed_forward.w2.weight', 'model.layers.21.attention_norm.weight', 'model.layers.21.ffn_norm.weight', 'model.layers.22.attention.wqkv.weight', 'model.layers.22.attention.wo.weight', 'model.layers.22.feed_forward.w1.weight', 'model.layers.22.feed_forward.w3.weight', 'model.layers.22.feed_forward.w2.weight', 'model.layers.22.attention_norm.weight', 'model.layers.22.ffn_norm.weight', 'model.layers.23.attention.wqkv.weight', 'model.layers.23.attention.wo.weight', 'model.layers.23.feed_forward.w1.weight', 'model.layers.23.feed_forward.w3.weight', 'model.layers.23.feed_forward.w2.weight', 'model.layers.23.attention_norm.weight', 'model.layers.23.ffn_norm.weight', 'model.layers.24.attention.wqkv.weight', 'model.layers.24.attention.wo.weight', 'model.layers.24.feed_forward.w1.weight', 'model.layers.24.feed_forward.w3.weight', 'model.layers.24.feed_forward.w2.weight', 'model.layers.24.attention_norm.weight', 'model.layers.24.ffn_norm.weight', 'model.layers.25.attention.wqkv.weight', 'model.layers.25.attention.wo.weight', 'model.layers.25.feed_forward.w1.weight', 'model.layers.25.feed_forward.w3.weight', 'model.layers.25.feed_forward.w2.weight', 'model.layers.25.attention_norm.weight', 'model.layers.25.ffn_norm.weight', 'model.layers.26.attention.wqkv.weight', 'model.layers.26.attention.wo.weight', 'model.layers.26.feed_forward.w1.weight', 'model.layers.26.feed_forward.w3.weight', 'model.layers.26.feed_forward.w2.weight', 'model.layers.26.attention_norm.weight', 'model.layers.26.ffn_norm.weight', 'model.layers.27.attention.wqkv.weight', 'model.layers.27.attention.wo.weight', 'model.layers.27.feed_forward.w1.weight', 'model.layers.27.feed_forward.w3.weight', 'model.layers.27.feed_forward.w2.weight', 'model.layers.27.attention_norm.weight', 'model.layers.27.ffn_norm.weight', 'model.layers.28.attention.wqkv.weight', 'model.layers.28.attention.wo.weight', 'model.layers.28.feed_forward.w1.weight', 'model.layers.28.feed_forward.w3.weight', 'model.layers.28.feed_forward.w2.weight', 'model.layers.28.attention_norm.weight', 'model.layers.28.ffn_norm.weight', 'model.layers.29.attention.wqkv.weight', 'model.layers.29.attention.wo.weight', 'model.layers.29.feed_forward.w1.weight', 'model.layers.29.feed_forward.w3.weight', 'model.layers.29.feed_forward.w2.weight', 'model.layers.29.attention_norm.weight', 'model.layers.29.ffn_norm.weight', 'model.layers.30.attention.wqkv.weight', 'model.layers.30.attention.wo.weight', 'model.layers.30.feed_forward.w1.weight', 'model.layers.30.feed_forward.w3.weight', 'model.layers.30.feed_forward.w2.weight', 'model.layers.30.attention_norm.weight', 'model.layers.30.ffn_norm.weight', 'model.layers.31.attention.wqkv.weight', 'model.layers.31.attention.wo.weight', 'model.layers.31.feed_forward.w1.weight', 'model.layers.31.feed_forward.w3.weight', 'model.layers.31.feed_forward.w2.weight', 'model.layers.31.attention_norm.weight', 'model.layers.31.ffn_norm.weight', 'model.layers.32.attention.wqkv.weight', 'model.layers.32.attention.wo.weight', 'model.layers.32.feed_forward.w1.weight', 'model.layers.32.feed_forward.w3.weight', 'model.layers.32.feed_forward.w2.weight', 'model.layers.32.attention_norm.weight', 'model.layers.32.ffn_norm.weight', 'model.layers.33.attention.wqkv.weight', 'model.layers.33.attention.wo.weight', 'model.layers.33.feed_forward.w1.weight', 'model.layers.33.feed_forward.w3.weight', 'model.layers.33.feed_forward.w2.weight', 'model.layers.33.attention_norm.weight', 'model.layers.33.ffn_norm.weight', 'model.layers.34.attention.wqkv.weight', 'model.layers.34.attention.wo.weight', 'model.layers.34.feed_forward.w1.weight', 'model.layers.34.feed_forward.w3.weight', 'model.layers.34.feed_forward.w2.weight', 'model.layers.34.attention_norm.weight', 'model.layers.34.ffn_norm.weight', 'model.layers.35.attention.wqkv.weight', 'model.layers.35.attention.wo.weight', 'model.layers.35.feed_forward.w1.weight', 'model.layers.35.feed_forward.w3.weight', 'model.layers.35.feed_forward.w2.weight', 'model.layers.35.attention_norm.weight', 'model.layers.35.ffn_norm.weight', 'model.layers.36.attention.wqkv.weight', 'model.layers.36.attention.wo.weight', 'model.layers.36.feed_forward.w1.weight', 'model.layers.36.feed_forward.w3.weight', 'model.layers.36.feed_forward.w2.weight', 'model.layers.36.attention_norm.weight', 'model.layers.36.ffn_norm.weight', 'model.layers.37.attention.wqkv.weight', 'model.layers.37.attention.wo.weight', 'model.layers.37.feed_forward.w1.weight', 'model.layers.37.feed_forward.w3.weight', 'model.layers.37.feed_forward.w2.weight', 'model.layers.37.attention_norm.weight', 'model.layers.37.ffn_norm.weight', 'model.layers.38.attention.wqkv.weight', 'model.layers.38.attention.wo.weight', 'model.layers.38.feed_forward.w1.weight', 'model.layers.38.feed_forward.w3.weight', 'model.layers.38.feed_forward.w2.weight', 'model.layers.38.attention_norm.weight', 'model.layers.38.ffn_norm.weight', 'model.layers.39.attention.wqkv.weight', 'model.layers.39.attention.wo.weight', 'model.layers.39.feed_forward.w1.weight', 'model.layers.39.feed_forward.w3.weight', 'model.layers.39.feed_forward.w2.weight', 'model.layers.39.attention_norm.weight', 'model.layers.39.ffn_norm.weight', 'model.layers.40.attention.wqkv.weight', 'model.layers.40.attention.wo.weight', 'model.layers.40.feed_forward.w1.weight', 'model.layers.40.feed_forward.w3.weight', 'model.layers.40.feed_forward.w2.weight', 'model.layers.40.attention_norm.weight', 'model.layers.40.ffn_norm.weight', 'model.layers.41.attention.wqkv.weight', 'model.layers.41.attention.wo.weight', 'model.layers.41.feed_forward.w1.weight', 'model.layers.41.feed_forward.w3.weight', 'model.layers.41.feed_forward.w2.weight', 'model.layers.41.attention_norm.weight', 'model.layers.41.ffn_norm.weight', 'model.layers.42.attention.wqkv.weight', 'model.layers.42.attention.wo.weight', 'model.layers.42.feed_forward.w1.weight', 'model.layers.42.feed_forward.w3.weight', 'model.layers.42.feed_forward.w2.weight', 'model.layers.42.attention_norm.weight', 'model.layers.42.ffn_norm.weight', 'model.layers.43.attention.wqkv.weight', 'model.layers.43.attention.wo.weight', 'model.layers.43.feed_forward.w1.weight', 'model.layers.43.feed_forward.w3.weight', 'model.layers.43.feed_forward.w2.weight', 'model.layers.43.attention_norm.weight', 'model.layers.43.ffn_norm.weight', 'model.layers.44.attention.wqkv.weight', 'model.layers.44.attention.wo.weight', 'model.layers.44.feed_forward.w1.weight', 'model.layers.44.feed_forward.w3.weight', 'model.layers.44.feed_forward.w2.weight', 'model.layers.44.attention_norm.weight', 'model.layers.44.ffn_norm.weight', 'model.layers.45.attention.wqkv.weight', 'model.layers.45.attention.wo.weight', 'model.layers.45.feed_forward.w1.weight', 'model.layers.45.feed_forward.w3.weight', 'model.layers.45.feed_forward.w2.weight', 'model.layers.45.attention_norm.weight', 'model.layers.45.ffn_norm.weight', 'model.layers.46.attention.wqkv.weight', 'model.layers.46.attention.wo.weight', 'model.layers.46.feed_forward.w1.weight', 'model.layers.46.feed_forward.w3.weight', 'model.layers.46.feed_forward.w2.weight', 'model.layers.46.attention_norm.weight', 'model.layers.46.ffn_norm.weight', 'model.layers.47.attention.wqkv.weight', 'model.layers.47.attention.wo.weight', 'model.layers.47.feed_forward.w1.weight', 'model.layers.47.feed_forward.w3.weight', 'model.layers.47.feed_forward.w2.weight', 'model.layers.47.attention_norm.weight', 'model.layers.47.ffn_norm.weight', 'model.norm.weight', 'output.weight'])"
-      ]
-     },
-     "execution_count": 24,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "b.keys()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "id": "b3725908-c731-41e0-92d2-3f7ed2926834",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "import torch\n",
-    "torch.cuda.empty_cache() "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "id": "18eb9972-f475-471e-9d3d-29b418dd01b4",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "b = {}"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "bb93ed26-2f16-4174-bd2b-93c7dd241daa",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "dic = []"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "57ef76ea-be23-48bd-8605-a8df99e3e991",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "for it in a.keys():\n",
-    "    dic.append(it)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 23,
-   "id": "db40fe6b-761f-4982-b3a3-f1d368be1f45",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "for it in a.keys():\n",
-    "    b[it.replace(\"language_model.\",\"\")] = a[it]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 25,
-   "id": "776afc7a-3237-419f-a808-fc37472de9ff",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "torch.save(b, \"pytorch_model.bin\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "b16a09b9-c25f-432d-929c-256cd5f21a3b",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.7"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}