{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "ZJjAmplaD4FG"
   },
   "outputs": [],
   "source": [
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "id": "At_60t8A92zP"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/home/ryn_mote/Misc/vlm_with_pooled_for_text_genrec\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/ryn_mote/anaconda3/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "e43c05fa9e374f2587356068d9343e08",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Some weights of the model checkpoint at OpenGVLab/InternVL2-4B were not used when initializing InternVLChatModel: ['vision_model.embeddings.class_embedding', 'vision_model.embeddings.patch_embedding.bias', 'vision_model.embeddings.patch_embedding.weight', 'vision_model.embeddings.position_embedding', 'vision_model.encoder.layers.0.attn.proj.bias', 'vision_model.encoder.layers.0.attn.proj.weight', 'vision_model.encoder.layers.0.attn.qkv.bias', 'vision_model.encoder.layers.0.attn.qkv.weight', 'vision_model.encoder.layers.0.ls1', 'vision_model.encoder.layers.0.ls2', 'vision_model.encoder.layers.0.mlp.fc1.bias', 'vision_model.encoder.layers.0.mlp.fc1.weight', 'vision_model.encoder.layers.0.mlp.fc2.bias', 'vision_model.encoder.layers.0.mlp.fc2.weight', 'vision_model.encoder.layers.0.norm1.bias', 'vision_model.encoder.layers.0.norm1.weight', 'vision_model.encoder.layers.0.norm2.bias', 'vision_model.encoder.layers.0.norm2.weight', 'vision_model.encoder.layers.1.attn.proj.bias', 'vision_model.encoder.layers.1.attn.proj.weight', 'vision_model.encoder.layers.1.attn.qkv.bias', 'vision_model.encoder.layers.1.attn.qkv.weight', 'vision_model.encoder.layers.1.ls1', 'vision_model.encoder.layers.1.ls2', 'vision_model.encoder.layers.1.mlp.fc1.bias', 'vision_model.encoder.layers.1.mlp.fc1.weight', 'vision_model.encoder.layers.1.mlp.fc2.bias', 'vision_model.encoder.layers.1.mlp.fc2.weight', 'vision_model.encoder.layers.1.norm1.bias', 'vision_model.encoder.layers.1.norm1.weight', 'vision_model.encoder.layers.1.norm2.bias', 'vision_model.encoder.layers.1.norm2.weight', 'vision_model.encoder.layers.10.attn.proj.bias', 'vision_model.encoder.layers.10.attn.proj.weight', 'vision_model.encoder.layers.10.attn.qkv.bias', 'vision_model.encoder.layers.10.attn.qkv.weight', 'vision_model.encoder.layers.10.ls1', 'vision_model.encoder.layers.10.ls2', 'vision_model.encoder.layers.10.mlp.fc1.bias', 'vision_model.encoder.layers.10.mlp.fc1.weight', 'vision_model.encoder.layers.10.mlp.fc2.bias', 'vision_model.encoder.layers.10.mlp.fc2.weight', 'vision_model.encoder.layers.10.norm1.bias', 'vision_model.encoder.layers.10.norm1.weight', 'vision_model.encoder.layers.10.norm2.bias', 'vision_model.encoder.layers.10.norm2.weight', 'vision_model.encoder.layers.11.attn.proj.bias', 'vision_model.encoder.layers.11.attn.proj.weight', 'vision_model.encoder.layers.11.attn.qkv.bias', 'vision_model.encoder.layers.11.attn.qkv.weight', 'vision_model.encoder.layers.11.ls1', 'vision_model.encoder.layers.11.ls2', 'vision_model.encoder.layers.11.mlp.fc1.bias', 'vision_model.encoder.layers.11.mlp.fc1.weight', 'vision_model.encoder.layers.11.mlp.fc2.bias', 'vision_model.encoder.layers.11.mlp.fc2.weight', 'vision_model.encoder.layers.11.norm1.bias', 'vision_model.encoder.layers.11.norm1.weight', 'vision_model.encoder.layers.11.norm2.bias', 'vision_model.encoder.layers.11.norm2.weight', 'vision_model.encoder.layers.12.attn.proj.bias', 'vision_model.encoder.layers.12.attn.proj.weight', 'vision_model.encoder.layers.12.attn.qkv.bias', 'vision_model.encoder.layers.12.attn.qkv.weight', 'vision_model.encoder.layers.12.ls1', 'vision_model.encoder.layers.12.ls2', 'vision_model.encoder.layers.12.mlp.fc1.bias', 'vision_model.encoder.layers.12.mlp.fc1.weight', 'vision_model.encoder.layers.12.mlp.fc2.bias', 'vision_model.encoder.layers.12.mlp.fc2.weight', 'vision_model.encoder.layers.12.norm1.bias', 'vision_model.encoder.layers.12.norm1.weight', 'vision_model.encoder.layers.12.norm2.bias', 'vision_model.encoder.layers.12.norm2.weight', 'vision_model.encoder.layers.13.attn.proj.bias', 'vision_model.encoder.layers.13.attn.proj.weight', 'vision_model.encoder.layers.13.attn.qkv.bias', 'vision_model.encoder.layers.13.attn.qkv.weight', 'vision_model.encoder.layers.13.ls1', 'vision_model.encoder.layers.13.ls2', 'vision_model.encoder.layers.13.mlp.fc1.bias', 'vision_model.encoder.layers.13.mlp.fc1.weight', 'vision_model.encoder.layers.13.mlp.fc2.bias', 'vision_model.encoder.layers.13.mlp.fc2.weight', 'vision_model.encoder.layers.13.norm1.bias', 'vision_model.encoder.layers.13.norm1.weight', 'vision_model.encoder.layers.13.norm2.bias', 'vision_model.encoder.layers.13.norm2.weight', 'vision_model.encoder.layers.14.attn.proj.bias', 'vision_model.encoder.layers.14.attn.proj.weight', 'vision_model.encoder.layers.14.attn.qkv.bias', 'vision_model.encoder.layers.14.attn.qkv.weight', 'vision_model.encoder.layers.14.ls1', 'vision_model.encoder.layers.14.ls2', 'vision_model.encoder.layers.14.mlp.fc1.bias', 'vision_model.encoder.layers.14.mlp.fc1.weight', 'vision_model.encoder.layers.14.mlp.fc2.bias', 'vision_model.encoder.layers.14.mlp.fc2.weight', 'vision_model.encoder.layers.14.norm1.bias', 'vision_model.encoder.layers.14.norm1.weight', 'vision_model.encoder.layers.14.norm2.bias', 'vision_model.encoder.layers.14.norm2.weight', 'vision_model.encoder.layers.15.attn.proj.bias', 'vision_model.encoder.layers.15.attn.proj.weight', 'vision_model.encoder.layers.15.attn.qkv.bias', 'vision_model.encoder.layers.15.attn.qkv.weight', 'vision_model.encoder.layers.15.ls1', 'vision_model.encoder.layers.15.ls2', 'vision_model.encoder.layers.15.mlp.fc1.bias', 'vision_model.encoder.layers.15.mlp.fc1.weight', 'vision_model.encoder.layers.15.mlp.fc2.bias', 'vision_model.encoder.layers.15.mlp.fc2.weight', 'vision_model.encoder.layers.15.norm1.bias', 'vision_model.encoder.layers.15.norm1.weight', 'vision_model.encoder.layers.15.norm2.bias', 'vision_model.encoder.layers.15.norm2.weight', 'vision_model.encoder.layers.16.attn.proj.bias', 'vision_model.encoder.layers.16.attn.proj.weight', 'vision_model.encoder.layers.16.attn.qkv.bias', 'vision_model.encoder.layers.16.attn.qkv.weight', 'vision_model.encoder.layers.16.ls1', 'vision_model.encoder.layers.16.ls2', 'vision_model.encoder.layers.16.mlp.fc1.bias', 'vision_model.encoder.layers.16.mlp.fc1.weight', 'vision_model.encoder.layers.16.mlp.fc2.bias', 'vision_model.encoder.layers.16.mlp.fc2.weight', 'vision_model.encoder.layers.16.norm1.bias', 'vision_model.encoder.layers.16.norm1.weight', 'vision_model.encoder.layers.16.norm2.bias', 'vision_model.encoder.layers.16.norm2.weight', 'vision_model.encoder.layers.17.attn.proj.bias', 'vision_model.encoder.layers.17.attn.proj.weight', 'vision_model.encoder.layers.17.attn.qkv.bias', 'vision_model.encoder.layers.17.attn.qkv.weight', 'vision_model.encoder.layers.17.ls1', 'vision_model.encoder.layers.17.ls2', 'vision_model.encoder.layers.17.mlp.fc1.bias', 'vision_model.encoder.layers.17.mlp.fc1.weight', 'vision_model.encoder.layers.17.mlp.fc2.bias', 'vision_model.encoder.layers.17.mlp.fc2.weight', 'vision_model.encoder.layers.17.norm1.bias', 'vision_model.encoder.layers.17.norm1.weight', 'vision_model.encoder.layers.17.norm2.bias', 'vision_model.encoder.layers.17.norm2.weight', 'vision_model.encoder.layers.18.attn.proj.bias', 'vision_model.encoder.layers.18.attn.proj.weight', 'vision_model.encoder.layers.18.attn.qkv.bias', 'vision_model.encoder.layers.18.attn.qkv.weight', 'vision_model.encoder.layers.18.ls1', 'vision_model.encoder.layers.18.ls2', 'vision_model.encoder.layers.18.mlp.fc1.bias', 'vision_model.encoder.layers.18.mlp.fc1.weight', 'vision_model.encoder.layers.18.mlp.fc2.bias', 'vision_model.encoder.layers.18.mlp.fc2.weight', 'vision_model.encoder.layers.18.norm1.bias', 'vision_model.encoder.layers.18.norm1.weight', 'vision_model.encoder.layers.18.norm2.bias', 'vision_model.encoder.layers.18.norm2.weight', 'vision_model.encoder.layers.19.attn.proj.bias', 'vision_model.encoder.layers.19.attn.proj.weight', 'vision_model.encoder.layers.19.attn.qkv.bias', 'vision_model.encoder.layers.19.attn.qkv.weight', 'vision_model.encoder.layers.19.ls1', 'vision_model.encoder.layers.19.ls2', 'vision_model.encoder.layers.19.mlp.fc1.bias', 'vision_model.encoder.layers.19.mlp.fc1.weight', 'vision_model.encoder.layers.19.mlp.fc2.bias', 'vision_model.encoder.layers.19.mlp.fc2.weight', 'vision_model.encoder.layers.19.norm1.bias', 'vision_model.encoder.layers.19.norm1.weight', 'vision_model.encoder.layers.19.norm2.bias', 'vision_model.encoder.layers.19.norm2.weight', 'vision_model.encoder.layers.2.attn.proj.bias', 'vision_model.encoder.layers.2.attn.proj.weight', 'vision_model.encoder.layers.2.attn.qkv.bias', 'vision_model.encoder.layers.2.attn.qkv.weight', 'vision_model.encoder.layers.2.ls1', 'vision_model.encoder.layers.2.ls2', 'vision_model.encoder.layers.2.mlp.fc1.bias', 'vision_model.encoder.layers.2.mlp.fc1.weight', 'vision_model.encoder.layers.2.mlp.fc2.bias', 'vision_model.encoder.layers.2.mlp.fc2.weight', 'vision_model.encoder.layers.2.norm1.bias', 'vision_model.encoder.layers.2.norm1.weight', 'vision_model.encoder.layers.2.norm2.bias', 'vision_model.encoder.layers.2.norm2.weight', 'vision_model.encoder.layers.20.attn.proj.bias', 'vision_model.encoder.layers.20.attn.proj.weight', 'vision_model.encoder.layers.20.attn.qkv.bias', 'vision_model.encoder.layers.20.attn.qkv.weight', 'vision_model.encoder.layers.20.ls1', 'vision_model.encoder.layers.20.ls2', 'vision_model.encoder.layers.20.mlp.fc1.bias', 'vision_model.encoder.layers.20.mlp.fc1.weight', 'vision_model.encoder.layers.20.mlp.fc2.bias', 'vision_model.encoder.layers.20.mlp.fc2.weight', 'vision_model.encoder.layers.20.norm1.bias', 'vision_model.encoder.layers.20.norm1.weight', 'vision_model.encoder.layers.20.norm2.bias', 'vision_model.encoder.layers.20.norm2.weight', 'vision_model.encoder.layers.21.attn.proj.bias', 'vision_model.encoder.layers.21.attn.proj.weight', 'vision_model.encoder.layers.21.attn.qkv.bias', 'vision_model.encoder.layers.21.attn.qkv.weight', 'vision_model.encoder.layers.21.ls1', 'vision_model.encoder.layers.21.ls2', 'vision_model.encoder.layers.21.mlp.fc1.bias', 'vision_model.encoder.layers.21.mlp.fc1.weight', 'vision_model.encoder.layers.21.mlp.fc2.bias', 'vision_model.encoder.layers.21.mlp.fc2.weight', 'vision_model.encoder.layers.21.norm1.bias', 'vision_model.encoder.layers.21.norm1.weight', 'vision_model.encoder.layers.21.norm2.bias', 'vision_model.encoder.layers.21.norm2.weight', 'vision_model.encoder.layers.22.attn.proj.bias', 'vision_model.encoder.layers.22.attn.proj.weight', 'vision_model.encoder.layers.22.attn.qkv.bias', 'vision_model.encoder.layers.22.attn.qkv.weight', 'vision_model.encoder.layers.22.ls1', 'vision_model.encoder.layers.22.ls2', 'vision_model.encoder.layers.22.mlp.fc1.bias', 'vision_model.encoder.layers.22.mlp.fc1.weight', 'vision_model.encoder.layers.22.mlp.fc2.bias', 'vision_model.encoder.layers.22.mlp.fc2.weight', 'vision_model.encoder.layers.22.norm1.bias', 'vision_model.encoder.layers.22.norm1.weight', 'vision_model.encoder.layers.22.norm2.bias', 'vision_model.encoder.layers.22.norm2.weight', 'vision_model.encoder.layers.23.attn.proj.bias', 'vision_model.encoder.layers.23.attn.proj.weight', 'vision_model.encoder.layers.23.attn.qkv.bias', 'vision_model.encoder.layers.23.attn.qkv.weight', 'vision_model.encoder.layers.23.ls1', 'vision_model.encoder.layers.23.ls2', 'vision_model.encoder.layers.23.mlp.fc1.bias', 'vision_model.encoder.layers.23.mlp.fc1.weight', 'vision_model.encoder.layers.23.mlp.fc2.bias', 'vision_model.encoder.layers.23.mlp.fc2.weight', 'vision_model.encoder.layers.23.norm1.bias', 'vision_model.encoder.layers.23.norm1.weight', 'vision_model.encoder.layers.23.norm2.bias', 'vision_model.encoder.layers.23.norm2.weight', 'vision_model.encoder.layers.3.attn.proj.bias', 'vision_model.encoder.layers.3.attn.proj.weight', 'vision_model.encoder.layers.3.attn.qkv.bias', 'vision_model.encoder.layers.3.attn.qkv.weight', 'vision_model.encoder.layers.3.ls1', 'vision_model.encoder.layers.3.ls2', 'vision_model.encoder.layers.3.mlp.fc1.bias', 'vision_model.encoder.layers.3.mlp.fc1.weight', 'vision_model.encoder.layers.3.mlp.fc2.bias', 'vision_model.encoder.layers.3.mlp.fc2.weight', 'vision_model.encoder.layers.3.norm1.bias', 'vision_model.encoder.layers.3.norm1.weight', 'vision_model.encoder.layers.3.norm2.bias', 'vision_model.encoder.layers.3.norm2.weight', 'vision_model.encoder.layers.4.attn.proj.bias', 'vision_model.encoder.layers.4.attn.proj.weight', 'vision_model.encoder.layers.4.attn.qkv.bias', 'vision_model.encoder.layers.4.attn.qkv.weight', 'vision_model.encoder.layers.4.ls1', 'vision_model.encoder.layers.4.ls2', 'vision_model.encoder.layers.4.mlp.fc1.bias', 'vision_model.encoder.layers.4.mlp.fc1.weight', 'vision_model.encoder.layers.4.mlp.fc2.bias', 'vision_model.encoder.layers.4.mlp.fc2.weight', 'vision_model.encoder.layers.4.norm1.bias', 'vision_model.encoder.layers.4.norm1.weight', 'vision_model.encoder.layers.4.norm2.bias', 'vision_model.encoder.layers.4.norm2.weight', 'vision_model.encoder.layers.5.attn.proj.bias', 'vision_model.encoder.layers.5.attn.proj.weight', 'vision_model.encoder.layers.5.attn.qkv.bias', 'vision_model.encoder.layers.5.attn.qkv.weight', 'vision_model.encoder.layers.5.ls1', 'vision_model.encoder.layers.5.ls2', 'vision_model.encoder.layers.5.mlp.fc1.bias', 'vision_model.encoder.layers.5.mlp.fc1.weight', 'vision_model.encoder.layers.5.mlp.fc2.bias', 'vision_model.encoder.layers.5.mlp.fc2.weight', 'vision_model.encoder.layers.5.norm1.bias', 'vision_model.encoder.layers.5.norm1.weight', 'vision_model.encoder.layers.5.norm2.bias', 'vision_model.encoder.layers.5.norm2.weight', 'vision_model.encoder.layers.6.attn.proj.bias', 'vision_model.encoder.layers.6.attn.proj.weight', 'vision_model.encoder.layers.6.attn.qkv.bias', 'vision_model.encoder.layers.6.attn.qkv.weight', 'vision_model.encoder.layers.6.ls1', 'vision_model.encoder.layers.6.ls2', 'vision_model.encoder.layers.6.mlp.fc1.bias', 'vision_model.encoder.layers.6.mlp.fc1.weight', 'vision_model.encoder.layers.6.mlp.fc2.bias', 'vision_model.encoder.layers.6.mlp.fc2.weight', 'vision_model.encoder.layers.6.norm1.bias', 'vision_model.encoder.layers.6.norm1.weight', 'vision_model.encoder.layers.6.norm2.bias', 'vision_model.encoder.layers.6.norm2.weight', 'vision_model.encoder.layers.7.attn.proj.bias', 'vision_model.encoder.layers.7.attn.proj.weight', 'vision_model.encoder.layers.7.attn.qkv.bias', 'vision_model.encoder.layers.7.attn.qkv.weight', 'vision_model.encoder.layers.7.ls1', 'vision_model.encoder.layers.7.ls2', 'vision_model.encoder.layers.7.mlp.fc1.bias', 'vision_model.encoder.layers.7.mlp.fc1.weight', 'vision_model.encoder.layers.7.mlp.fc2.bias', 'vision_model.encoder.layers.7.mlp.fc2.weight', 'vision_model.encoder.layers.7.norm1.bias', 'vision_model.encoder.layers.7.norm1.weight', 'vision_model.encoder.layers.7.norm2.bias', 'vision_model.encoder.layers.7.norm2.weight', 'vision_model.encoder.layers.8.attn.proj.bias', 'vision_model.encoder.layers.8.attn.proj.weight', 'vision_model.encoder.layers.8.attn.qkv.bias', 'vision_model.encoder.layers.8.attn.qkv.weight', 'vision_model.encoder.layers.8.ls1', 'vision_model.encoder.layers.8.ls2', 'vision_model.encoder.layers.8.mlp.fc1.bias', 'vision_model.encoder.layers.8.mlp.fc1.weight', 'vision_model.encoder.layers.8.mlp.fc2.bias', 'vision_model.encoder.layers.8.mlp.fc2.weight', 'vision_model.encoder.layers.8.norm1.bias', 'vision_model.encoder.layers.8.norm1.weight', 'vision_model.encoder.layers.8.norm2.bias', 'vision_model.encoder.layers.8.norm2.weight', 'vision_model.encoder.layers.9.attn.proj.bias', 'vision_model.encoder.layers.9.attn.proj.weight', 'vision_model.encoder.layers.9.attn.qkv.bias', 'vision_model.encoder.layers.9.attn.qkv.weight', 'vision_model.encoder.layers.9.ls1', 'vision_model.encoder.layers.9.ls2', 'vision_model.encoder.layers.9.mlp.fc1.bias', 'vision_model.encoder.layers.9.mlp.fc1.weight', 'vision_model.encoder.layers.9.mlp.fc2.bias', 'vision_model.encoder.layers.9.mlp.fc2.weight', 'vision_model.encoder.layers.9.norm1.bias', 'vision_model.encoder.layers.9.norm1.weight', 'vision_model.encoder.layers.9.norm2.bias', 'vision_model.encoder.layers.9.norm2.weight']\n",
      "- This IS expected if you are initializing InternVLChatModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
      "- This IS NOT expected if you are initializing InternVLChatModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
      "Some weights of InternVLChatModel were not initialized from the model checkpoint at OpenGVLab/InternVL2-4B and are newly initialized: ['vision_model.logit_scale', 'vision_model.text_model.embeddings.position_embedding.weight', 'vision_model.text_model.embeddings.token_embedding.weight', 'vision_model.text_model.encoder.layers.0.layer_norm1.bias', 'vision_model.text_model.encoder.layers.0.layer_norm1.weight', 'vision_model.text_model.encoder.layers.0.layer_norm2.bias', 'vision_model.text_model.encoder.layers.0.layer_norm2.weight', 'vision_model.text_model.encoder.layers.0.mlp.fc1.bias', 'vision_model.text_model.encoder.layers.0.mlp.fc1.weight', 'vision_model.text_model.encoder.layers.0.mlp.fc2.bias', 'vision_model.text_model.encoder.layers.0.mlp.fc2.weight', 'vision_model.text_model.encoder.layers.0.self_attn.k_proj.bias', 'vision_model.text_model.encoder.layers.0.self_attn.k_proj.weight', 'vision_model.text_model.encoder.layers.0.self_attn.out_proj.bias', 'vision_model.text_model.encoder.layers.0.self_attn.out_proj.weight', 'vision_model.text_model.encoder.layers.0.self_attn.q_proj.bias', 'vision_model.text_model.encoder.layers.0.self_attn.q_proj.weight', 'vision_model.text_model.encoder.layers.0.self_attn.v_proj.bias', 'vision_model.text_model.encoder.layers.0.self_attn.v_proj.weight', 'vision_model.text_model.encoder.layers.1.layer_norm1.bias', 'vision_model.text_model.encoder.layers.1.layer_norm1.weight', 'vision_model.text_model.encoder.layers.1.layer_norm2.bias', 'vision_model.text_model.encoder.layers.1.layer_norm2.weight', 'vision_model.text_model.encoder.layers.1.mlp.fc1.bias', 'vision_model.text_model.encoder.layers.1.mlp.fc1.weight', 'vision_model.text_model.encoder.layers.1.mlp.fc2.bias', 'vision_model.text_model.encoder.layers.1.mlp.fc2.weight', 'vision_model.text_model.encoder.layers.1.self_attn.k_proj.bias', 'vision_model.text_model.encoder.layers.1.self_attn.k_proj.weight', 'vision_model.text_model.encoder.layers.1.self_attn.out_proj.bias', 'vision_model.text_model.encoder.layers.1.self_attn.out_proj.weight', 'vision_model.text_model.encoder.layers.1.self_attn.q_proj.bias', 'vision_model.text_model.encoder.layers.1.self_attn.q_proj.weight', 'vision_model.text_model.encoder.layers.1.self_attn.v_proj.bias', 'vision_model.text_model.encoder.layers.1.self_attn.v_proj.weight', 'vision_model.text_model.encoder.layers.10.layer_norm1.bias', 'vision_model.text_model.encoder.layers.10.layer_norm1.weight', 'vision_model.text_model.encoder.layers.10.layer_norm2.bias', 'vision_model.text_model.encoder.layers.10.layer_norm2.weight', 'vision_model.text_model.encoder.layers.10.mlp.fc1.bias', 'vision_model.text_model.encoder.layers.10.mlp.fc1.weight', 'vision_model.text_model.encoder.layers.10.mlp.fc2.bias', 'vision_model.text_model.encoder.layers.10.mlp.fc2.weight', 'vision_model.text_model.encoder.layers.10.self_attn.k_proj.bias', 'vision_model.text_model.encoder.layers.10.self_attn.k_proj.weight', 'vision_model.text_model.encoder.layers.10.self_attn.out_proj.bias', 'vision_model.text_model.encoder.layers.10.self_attn.out_proj.weight', 'vision_model.text_model.encoder.layers.10.self_attn.q_proj.bias', 'vision_model.text_model.encoder.layers.10.self_attn.q_proj.weight', 'vision_model.text_model.encoder.layers.10.self_attn.v_proj.bias', 'vision_model.text_model.encoder.layers.10.self_attn.v_proj.weight', 'vision_model.text_model.encoder.layers.11.layer_norm1.bias', 'vision_model.text_model.encoder.layers.11.layer_norm1.weight', 'vision_model.text_model.encoder.layers.11.layer_norm2.bias', 'vision_model.text_model.encoder.layers.11.layer_norm2.weight', 'vision_model.text_model.encoder.layers.11.mlp.fc1.bias', 'vision_model.text_model.encoder.layers.11.mlp.fc1.weight', 'vision_model.text_model.encoder.layers.11.mlp.fc2.bias', 'vision_model.text_model.encoder.layers.11.mlp.fc2.weight', 'vision_model.text_model.encoder.layers.11.self_attn.k_proj.bias', 'vision_model.text_model.encoder.layers.11.self_attn.k_proj.weight', 'vision_model.text_model.encoder.layers.11.self_attn.out_proj.bias', 'vision_model.text_model.encoder.layers.11.self_attn.out_proj.weight', 'vision_model.text_model.encoder.layers.11.self_attn.q_proj.bias', 'vision_model.text_model.encoder.layers.11.self_attn.q_proj.weight', 'vision_model.text_model.encoder.layers.11.self_attn.v_proj.bias', 'vision_model.text_model.encoder.layers.11.self_attn.v_proj.weight', 'vision_model.text_model.encoder.layers.2.layer_norm1.bias', 'vision_model.text_model.encoder.layers.2.layer_norm1.weight', 'vision_model.text_model.encoder.layers.2.layer_norm2.bias', 'vision_model.text_model.encoder.layers.2.layer_norm2.weight', 'vision_model.text_model.encoder.layers.2.mlp.fc1.bias', 'vision_model.text_model.encoder.layers.2.mlp.fc1.weight', 'vision_model.text_model.encoder.layers.2.mlp.fc2.bias', 'vision_model.text_model.encoder.layers.2.mlp.fc2.weight', 'vision_model.text_model.encoder.layers.2.self_attn.k_proj.bias', 'vision_model.text_model.encoder.layers.2.self_attn.k_proj.weight', 'vision_model.text_model.encoder.layers.2.self_attn.out_proj.bias', 'vision_model.text_model.encoder.layers.2.self_attn.out_proj.weight', 'vision_model.text_model.encoder.layers.2.self_attn.q_proj.bias', 'vision_model.text_model.encoder.layers.2.self_attn.q_proj.weight', 'vision_model.text_model.encoder.layers.2.self_attn.v_proj.bias', 'vision_model.text_model.encoder.layers.2.self_attn.v_proj.weight', 'vision_model.text_model.encoder.layers.3.layer_norm1.bias', 'vision_model.text_model.encoder.layers.3.layer_norm1.weight', 'vision_model.text_model.encoder.layers.3.layer_norm2.bias', 'vision_model.text_model.encoder.layers.3.layer_norm2.weight', 'vision_model.text_model.encoder.layers.3.mlp.fc1.bias', 'vision_model.text_model.encoder.layers.3.mlp.fc1.weight', 'vision_model.text_model.encoder.layers.3.mlp.fc2.bias', 'vision_model.text_model.encoder.layers.3.mlp.fc2.weight', 'vision_model.text_model.encoder.layers.3.self_attn.k_proj.bias', 'vision_model.text_model.encoder.layers.3.self_attn.k_proj.weight', 'vision_model.text_model.encoder.layers.3.self_attn.out_proj.bias', 'vision_model.text_model.encoder.layers.3.self_attn.out_proj.weight', 'vision_model.text_model.encoder.layers.3.self_attn.q_proj.bias', 'vision_model.text_model.encoder.layers.3.self_attn.q_proj.weight', 'vision_model.text_model.encoder.layers.3.self_attn.v_proj.bias', 'vision_model.text_model.encoder.layers.3.self_attn.v_proj.weight', 'vision_model.text_model.encoder.layers.4.layer_norm1.bias', 'vision_model.text_model.encoder.layers.4.layer_norm1.weight', 'vision_model.text_model.encoder.layers.4.layer_norm2.bias', 'vision_model.text_model.encoder.layers.4.layer_norm2.weight', 'vision_model.text_model.encoder.layers.4.mlp.fc1.bias', 'vision_model.text_model.encoder.layers.4.mlp.fc1.weight', 'vision_model.text_model.encoder.layers.4.mlp.fc2.bias', 'vision_model.text_model.encoder.layers.4.mlp.fc2.weight', 'vision_model.text_model.encoder.layers.4.self_attn.k_proj.bias', 'vision_model.text_model.encoder.layers.4.self_attn.k_proj.weight', 'vision_model.text_model.encoder.layers.4.self_attn.out_proj.bias', 'vision_model.text_model.encoder.layers.4.self_attn.out_proj.weight', 'vision_model.text_model.encoder.layers.4.self_attn.q_proj.bias', 'vision_model.text_model.encoder.layers.4.self_attn.q_proj.weight', 'vision_model.text_model.encoder.layers.4.self_attn.v_proj.bias', 'vision_model.text_model.encoder.layers.4.self_attn.v_proj.weight', 'vision_model.text_model.encoder.layers.5.layer_norm1.bias', 'vision_model.text_model.encoder.layers.5.layer_norm1.weight', 'vision_model.text_model.encoder.layers.5.layer_norm2.bias', 'vision_model.text_model.encoder.layers.5.layer_norm2.weight', 'vision_model.text_model.encoder.layers.5.mlp.fc1.bias', 'vision_model.text_model.encoder.layers.5.mlp.fc1.weight', 'vision_model.text_model.encoder.layers.5.mlp.fc2.bias', 'vision_model.text_model.encoder.layers.5.mlp.fc2.weight', 'vision_model.text_model.encoder.layers.5.self_attn.k_proj.bias', 'vision_model.text_model.encoder.layers.5.self_attn.k_proj.weight', 'vision_model.text_model.encoder.layers.5.self_attn.out_proj.bias', 'vision_model.text_model.encoder.layers.5.self_attn.out_proj.weight', 'vision_model.text_model.encoder.layers.5.self_attn.q_proj.bias', 'vision_model.text_model.encoder.layers.5.self_attn.q_proj.weight', 'vision_model.text_model.encoder.layers.5.self_attn.v_proj.bias', 'vision_model.text_model.encoder.layers.5.self_attn.v_proj.weight', 'vision_model.text_model.encoder.layers.6.layer_norm1.bias', 'vision_model.text_model.encoder.layers.6.layer_norm1.weight', 'vision_model.text_model.encoder.layers.6.layer_norm2.bias', 'vision_model.text_model.encoder.layers.6.layer_norm2.weight', 'vision_model.text_model.encoder.layers.6.mlp.fc1.bias', 'vision_model.text_model.encoder.layers.6.mlp.fc1.weight', 'vision_model.text_model.encoder.layers.6.mlp.fc2.bias', 'vision_model.text_model.encoder.layers.6.mlp.fc2.weight', 'vision_model.text_model.encoder.layers.6.self_attn.k_proj.bias', 'vision_model.text_model.encoder.layers.6.self_attn.k_proj.weight', 'vision_model.text_model.encoder.layers.6.self_attn.out_proj.bias', 'vision_model.text_model.encoder.layers.6.self_attn.out_proj.weight', 'vision_model.text_model.encoder.layers.6.self_attn.q_proj.bias', 'vision_model.text_model.encoder.layers.6.self_attn.q_proj.weight', 'vision_model.text_model.encoder.layers.6.self_attn.v_proj.bias', 'vision_model.text_model.encoder.layers.6.self_attn.v_proj.weight', 'vision_model.text_model.encoder.layers.7.layer_norm1.bias', 'vision_model.text_model.encoder.layers.7.layer_norm1.weight', 'vision_model.text_model.encoder.layers.7.layer_norm2.bias', 'vision_model.text_model.encoder.layers.7.layer_norm2.weight', 'vision_model.text_model.encoder.layers.7.mlp.fc1.bias', 'vision_model.text_model.encoder.layers.7.mlp.fc1.weight', 'vision_model.text_model.encoder.layers.7.mlp.fc2.bias', 'vision_model.text_model.encoder.layers.7.mlp.fc2.weight', 'vision_model.text_model.encoder.layers.7.self_attn.k_proj.bias', 'vision_model.text_model.encoder.layers.7.self_attn.k_proj.weight', 'vision_model.text_model.encoder.layers.7.self_attn.out_proj.bias', 'vision_model.text_model.encoder.layers.7.self_attn.out_proj.weight', 'vision_model.text_model.encoder.layers.7.self_attn.q_proj.bias', 'vision_model.text_model.encoder.layers.7.self_attn.q_proj.weight', 'vision_model.text_model.encoder.layers.7.self_attn.v_proj.bias', 'vision_model.text_model.encoder.layers.7.self_attn.v_proj.weight', 'vision_model.text_model.encoder.layers.8.layer_norm1.bias', 'vision_model.text_model.encoder.layers.8.layer_norm1.weight', 'vision_model.text_model.encoder.layers.8.layer_norm2.bias', 'vision_model.text_model.encoder.layers.8.layer_norm2.weight', 'vision_model.text_model.encoder.layers.8.mlp.fc1.bias', 'vision_model.text_model.encoder.layers.8.mlp.fc1.weight', 'vision_model.text_model.encoder.layers.8.mlp.fc2.bias', 'vision_model.text_model.encoder.layers.8.mlp.fc2.weight', 'vision_model.text_model.encoder.layers.8.self_attn.k_proj.bias', 'vision_model.text_model.encoder.layers.8.self_attn.k_proj.weight', 'vision_model.text_model.encoder.layers.8.self_attn.out_proj.bias', 'vision_model.text_model.encoder.layers.8.self_attn.out_proj.weight', 'vision_model.text_model.encoder.layers.8.self_attn.q_proj.bias', 'vision_model.text_model.encoder.layers.8.self_attn.q_proj.weight', 'vision_model.text_model.encoder.layers.8.self_attn.v_proj.bias', 'vision_model.text_model.encoder.layers.8.self_attn.v_proj.weight', 'vision_model.text_model.encoder.layers.9.layer_norm1.bias', 'vision_model.text_model.encoder.layers.9.layer_norm1.weight', 'vision_model.text_model.encoder.layers.9.layer_norm2.bias', 'vision_model.text_model.encoder.layers.9.layer_norm2.weight', 'vision_model.text_model.encoder.layers.9.mlp.fc1.bias', 'vision_model.text_model.encoder.layers.9.mlp.fc1.weight', 'vision_model.text_model.encoder.layers.9.mlp.fc2.bias', 'vision_model.text_model.encoder.layers.9.mlp.fc2.weight', 'vision_model.text_model.encoder.layers.9.self_attn.k_proj.bias', 'vision_model.text_model.encoder.layers.9.self_attn.k_proj.weight', 'vision_model.text_model.encoder.layers.9.self_attn.out_proj.bias', 'vision_model.text_model.encoder.layers.9.self_attn.out_proj.weight', 'vision_model.text_model.encoder.layers.9.self_attn.q_proj.bias', 'vision_model.text_model.encoder.layers.9.self_attn.q_proj.weight', 'vision_model.text_model.encoder.layers.9.self_attn.v_proj.bias', 'vision_model.text_model.encoder.layers.9.self_attn.v_proj.weight', 'vision_model.text_model.final_layer_norm.bias', 'vision_model.text_model.final_layer_norm.weight', 'vision_model.text_projection.weight', 'vision_model.vision_model.embeddings.class_embedding', 'vision_model.vision_model.embeddings.patch_embedding.weight', 'vision_model.vision_model.embeddings.position_embedding.weight', 'vision_model.vision_model.encoder.layers.0.layer_norm1.bias', 'vision_model.vision_model.encoder.layers.0.layer_norm1.weight', 'vision_model.vision_model.encoder.layers.0.layer_norm2.bias', 'vision_model.vision_model.encoder.layers.0.layer_norm2.weight', 'vision_model.vision_model.encoder.layers.0.mlp.fc1.bias', 'vision_model.vision_model.encoder.layers.0.mlp.fc1.weight', 'vision_model.vision_model.encoder.layers.0.mlp.fc2.bias', 'vision_model.vision_model.encoder.layers.0.mlp.fc2.weight', 'vision_model.vision_model.encoder.layers.0.self_attn.k_proj.bias', 'vision_model.vision_model.encoder.layers.0.self_attn.k_proj.weight', 'vision_model.vision_model.encoder.layers.0.self_attn.out_proj.bias', 'vision_model.vision_model.encoder.layers.0.self_attn.out_proj.weight', 'vision_model.vision_model.encoder.layers.0.self_attn.q_proj.bias', 'vision_model.vision_model.encoder.layers.0.self_attn.q_proj.weight', 'vision_model.vision_model.encoder.layers.0.self_attn.v_proj.bias', 'vision_model.vision_model.encoder.layers.0.self_attn.v_proj.weight', 'vision_model.vision_model.encoder.layers.1.layer_norm1.bias', 'vision_model.vision_model.encoder.layers.1.layer_norm1.weight', 'vision_model.vision_model.encoder.layers.1.layer_norm2.bias', 'vision_model.vision_model.encoder.layers.1.layer_norm2.weight', 'vision_model.vision_model.encoder.layers.1.mlp.fc1.bias', 'vision_model.vision_model.encoder.layers.1.mlp.fc1.weight', 'vision_model.vision_model.encoder.layers.1.mlp.fc2.bias', 'vision_model.vision_model.encoder.layers.1.mlp.fc2.weight', 'vision_model.vision_model.encoder.layers.1.self_attn.k_proj.bias', 'vision_model.vision_model.encoder.layers.1.self_attn.k_proj.weight', 'vision_model.vision_model.encoder.layers.1.self_attn.out_proj.bias', 'vision_model.vision_model.encoder.layers.1.self_attn.out_proj.weight', 'vision_model.vision_model.encoder.layers.1.self_attn.q_proj.bias', 'vision_model.vision_model.encoder.layers.1.self_attn.q_proj.weight', 'vision_model.vision_model.encoder.layers.1.self_attn.v_proj.bias', 'vision_model.vision_model.encoder.layers.1.self_attn.v_proj.weight', 'vision_model.vision_model.encoder.layers.10.layer_norm1.bias', 'vision_model.vision_model.encoder.layers.10.layer_norm1.weight', 'vision_model.vision_model.encoder.layers.10.layer_norm2.bias', 'vision_model.vision_model.encoder.layers.10.layer_norm2.weight', 'vision_model.vision_model.encoder.layers.10.mlp.fc1.bias', 'vision_model.vision_model.encoder.layers.10.mlp.fc1.weight', 'vision_model.vision_model.encoder.layers.10.mlp.fc2.bias', 'vision_model.vision_model.encoder.layers.10.mlp.fc2.weight', 'vision_model.vision_model.encoder.layers.10.self_attn.k_proj.bias', 'vision_model.vision_model.encoder.layers.10.self_attn.k_proj.weight', 'vision_model.vision_model.encoder.layers.10.self_attn.out_proj.bias', 'vision_model.vision_model.encoder.layers.10.self_attn.out_proj.weight', 'vision_model.vision_model.encoder.layers.10.self_attn.q_proj.bias', 'vision_model.vision_model.encoder.layers.10.self_attn.q_proj.weight', 'vision_model.vision_model.encoder.layers.10.self_attn.v_proj.bias', 'vision_model.vision_model.encoder.layers.10.self_attn.v_proj.weight', 'vision_model.vision_model.encoder.layers.11.layer_norm1.bias', 'vision_model.vision_model.encoder.layers.11.layer_norm1.weight', 'vision_model.vision_model.encoder.layers.11.layer_norm2.bias', 'vision_model.vision_model.encoder.layers.11.layer_norm2.weight', 'vision_model.vision_model.encoder.layers.11.mlp.fc1.bias', 'vision_model.vision_model.encoder.layers.11.mlp.fc1.weight', 'vision_model.vision_model.encoder.layers.11.mlp.fc2.bias', 'vision_model.vision_model.encoder.layers.11.mlp.fc2.weight', 'vision_model.vision_model.encoder.layers.11.self_attn.k_proj.bias', 'vision_model.vision_model.encoder.layers.11.self_attn.k_proj.weight', 'vision_model.vision_model.encoder.layers.11.self_attn.out_proj.bias', 'vision_model.vision_model.encoder.layers.11.self_attn.out_proj.weight', 'vision_model.vision_model.encoder.layers.11.self_attn.q_proj.bias', 'vision_model.vision_model.encoder.layers.11.self_attn.q_proj.weight', 'vision_model.vision_model.encoder.layers.11.self_attn.v_proj.bias', 'vision_model.vision_model.encoder.layers.11.self_attn.v_proj.weight', 'vision_model.vision_model.encoder.layers.2.layer_norm1.bias', 'vision_model.vision_model.encoder.layers.2.layer_norm1.weight', 'vision_model.vision_model.encoder.layers.2.layer_norm2.bias', 'vision_model.vision_model.encoder.layers.2.layer_norm2.weight', 'vision_model.vision_model.encoder.layers.2.mlp.fc1.bias', 'vision_model.vision_model.encoder.layers.2.mlp.fc1.weight', 'vision_model.vision_model.encoder.layers.2.mlp.fc2.bias', 'vision_model.vision_model.encoder.layers.2.mlp.fc2.weight', 'vision_model.vision_model.encoder.layers.2.self_attn.k_proj.bias', 'vision_model.vision_model.encoder.layers.2.self_attn.k_proj.weight', 'vision_model.vision_model.encoder.layers.2.self_attn.out_proj.bias', 'vision_model.vision_model.encoder.layers.2.self_attn.out_proj.weight', 'vision_model.vision_model.encoder.layers.2.self_attn.q_proj.bias', 'vision_model.vision_model.encoder.layers.2.self_attn.q_proj.weight', 'vision_model.vision_model.encoder.layers.2.self_attn.v_proj.bias', 'vision_model.vision_model.encoder.layers.2.self_attn.v_proj.weight', 'vision_model.vision_model.encoder.layers.3.layer_norm1.bias', 'vision_model.vision_model.encoder.layers.3.layer_norm1.weight', 'vision_model.vision_model.encoder.layers.3.layer_norm2.bias', 'vision_model.vision_model.encoder.layers.3.layer_norm2.weight', 'vision_model.vision_model.encoder.layers.3.mlp.fc1.bias', 'vision_model.vision_model.encoder.layers.3.mlp.fc1.weight', 'vision_model.vision_model.encoder.layers.3.mlp.fc2.bias', 'vision_model.vision_model.encoder.layers.3.mlp.fc2.weight', 'vision_model.vision_model.encoder.layers.3.self_attn.k_proj.bias', 'vision_model.vision_model.encoder.layers.3.self_attn.k_proj.weight', 'vision_model.vision_model.encoder.layers.3.self_attn.out_proj.bias', 'vision_model.vision_model.encoder.layers.3.self_attn.out_proj.weight', 'vision_model.vision_model.encoder.layers.3.self_attn.q_proj.bias', 'vision_model.vision_model.encoder.layers.3.self_attn.q_proj.weight', 'vision_model.vision_model.encoder.layers.3.self_attn.v_proj.bias', 'vision_model.vision_model.encoder.layers.3.self_attn.v_proj.weight', 'vision_model.vision_model.encoder.layers.4.layer_norm1.bias', 'vision_model.vision_model.encoder.layers.4.layer_norm1.weight', 'vision_model.vision_model.encoder.layers.4.layer_norm2.bias', 'vision_model.vision_model.encoder.layers.4.layer_norm2.weight', 'vision_model.vision_model.encoder.layers.4.mlp.fc1.bias', 'vision_model.vision_model.encoder.layers.4.mlp.fc1.weight', 'vision_model.vision_model.encoder.layers.4.mlp.fc2.bias', 'vision_model.vision_model.encoder.layers.4.mlp.fc2.weight', 'vision_model.vision_model.encoder.layers.4.self_attn.k_proj.bias', 'vision_model.vision_model.encoder.layers.4.self_attn.k_proj.weight', 'vision_model.vision_model.encoder.layers.4.self_attn.out_proj.bias', 'vision_model.vision_model.encoder.layers.4.self_attn.out_proj.weight', 'vision_model.vision_model.encoder.layers.4.self_attn.q_proj.bias', 'vision_model.vision_model.encoder.layers.4.self_attn.q_proj.weight', 'vision_model.vision_model.encoder.layers.4.self_attn.v_proj.bias', 'vision_model.vision_model.encoder.layers.4.self_attn.v_proj.weight', 'vision_model.vision_model.encoder.layers.5.layer_norm1.bias', 'vision_model.vision_model.encoder.layers.5.layer_norm1.weight', 'vision_model.vision_model.encoder.layers.5.layer_norm2.bias', 'vision_model.vision_model.encoder.layers.5.layer_norm2.weight', 'vision_model.vision_model.encoder.layers.5.mlp.fc1.bias', 'vision_model.vision_model.encoder.layers.5.mlp.fc1.weight', 'vision_model.vision_model.encoder.layers.5.mlp.fc2.bias', 'vision_model.vision_model.encoder.layers.5.mlp.fc2.weight', 'vision_model.vision_model.encoder.layers.5.self_attn.k_proj.bias', 'vision_model.vision_model.encoder.layers.5.self_attn.k_proj.weight', 'vision_model.vision_model.encoder.layers.5.self_attn.out_proj.bias', 'vision_model.vision_model.encoder.layers.5.self_attn.out_proj.weight', 'vision_model.vision_model.encoder.layers.5.self_attn.q_proj.bias', 'vision_model.vision_model.encoder.layers.5.self_attn.q_proj.weight', 'vision_model.vision_model.encoder.layers.5.self_attn.v_proj.bias', 'vision_model.vision_model.encoder.layers.5.self_attn.v_proj.weight', 'vision_model.vision_model.encoder.layers.6.layer_norm1.bias', 'vision_model.vision_model.encoder.layers.6.layer_norm1.weight', 'vision_model.vision_model.encoder.layers.6.layer_norm2.bias', 'vision_model.vision_model.encoder.layers.6.layer_norm2.weight', 'vision_model.vision_model.encoder.layers.6.mlp.fc1.bias', 'vision_model.vision_model.encoder.layers.6.mlp.fc1.weight', 'vision_model.vision_model.encoder.layers.6.mlp.fc2.bias', 'vision_model.vision_model.encoder.layers.6.mlp.fc2.weight', 'vision_model.vision_model.encoder.layers.6.self_attn.k_proj.bias', 'vision_model.vision_model.encoder.layers.6.self_attn.k_proj.weight', 'vision_model.vision_model.encoder.layers.6.self_attn.out_proj.bias', 'vision_model.vision_model.encoder.layers.6.self_attn.out_proj.weight', 'vision_model.vision_model.encoder.layers.6.self_attn.q_proj.bias', 'vision_model.vision_model.encoder.layers.6.self_attn.q_proj.weight', 'vision_model.vision_model.encoder.layers.6.self_attn.v_proj.bias', 'vision_model.vision_model.encoder.layers.6.self_attn.v_proj.weight', 'vision_model.vision_model.encoder.layers.7.layer_norm1.bias', 'vision_model.vision_model.encoder.layers.7.layer_norm1.weight', 'vision_model.vision_model.encoder.layers.7.layer_norm2.bias', 'vision_model.vision_model.encoder.layers.7.layer_norm2.weight', 'vision_model.vision_model.encoder.layers.7.mlp.fc1.bias', 'vision_model.vision_model.encoder.layers.7.mlp.fc1.weight', 'vision_model.vision_model.encoder.layers.7.mlp.fc2.bias', 'vision_model.vision_model.encoder.layers.7.mlp.fc2.weight', 'vision_model.vision_model.encoder.layers.7.self_attn.k_proj.bias', 'vision_model.vision_model.encoder.layers.7.self_attn.k_proj.weight', 'vision_model.vision_model.encoder.layers.7.self_attn.out_proj.bias', 'vision_model.vision_model.encoder.layers.7.self_attn.out_proj.weight', 'vision_model.vision_model.encoder.layers.7.self_attn.q_proj.bias', 'vision_model.vision_model.encoder.layers.7.self_attn.q_proj.weight', 'vision_model.vision_model.encoder.layers.7.self_attn.v_proj.bias', 'vision_model.vision_model.encoder.layers.7.self_attn.v_proj.weight', 'vision_model.vision_model.encoder.layers.8.layer_norm1.bias', 'vision_model.vision_model.encoder.layers.8.layer_norm1.weight', 'vision_model.vision_model.encoder.layers.8.layer_norm2.bias', 'vision_model.vision_model.encoder.layers.8.layer_norm2.weight', 'vision_model.vision_model.encoder.layers.8.mlp.fc1.bias', 'vision_model.vision_model.encoder.layers.8.mlp.fc1.weight', 'vision_model.vision_model.encoder.layers.8.mlp.fc2.bias', 'vision_model.vision_model.encoder.layers.8.mlp.fc2.weight', 'vision_model.vision_model.encoder.layers.8.self_attn.k_proj.bias', 'vision_model.vision_model.encoder.layers.8.self_attn.k_proj.weight', 'vision_model.vision_model.encoder.layers.8.self_attn.out_proj.bias', 'vision_model.vision_model.encoder.layers.8.self_attn.out_proj.weight', 'vision_model.vision_model.encoder.layers.8.self_attn.q_proj.bias', 'vision_model.vision_model.encoder.layers.8.self_attn.q_proj.weight', 'vision_model.vision_model.encoder.layers.8.self_attn.v_proj.bias', 'vision_model.vision_model.encoder.layers.8.self_attn.v_proj.weight', 'vision_model.vision_model.encoder.layers.9.layer_norm1.bias', 'vision_model.vision_model.encoder.layers.9.layer_norm1.weight', 'vision_model.vision_model.encoder.layers.9.layer_norm2.bias', 'vision_model.vision_model.encoder.layers.9.layer_norm2.weight', 'vision_model.vision_model.encoder.layers.9.mlp.fc1.bias', 'vision_model.vision_model.encoder.layers.9.mlp.fc1.weight', 'vision_model.vision_model.encoder.layers.9.mlp.fc2.bias', 'vision_model.vision_model.encoder.layers.9.mlp.fc2.weight', 'vision_model.vision_model.encoder.layers.9.self_attn.k_proj.bias', 'vision_model.vision_model.encoder.layers.9.self_attn.k_proj.weight', 'vision_model.vision_model.encoder.layers.9.self_attn.out_proj.bias', 'vision_model.vision_model.encoder.layers.9.self_attn.out_proj.weight', 'vision_model.vision_model.encoder.layers.9.self_attn.q_proj.bias', 'vision_model.vision_model.encoder.layers.9.self_attn.q_proj.weight', 'vision_model.vision_model.encoder.layers.9.self_attn.v_proj.bias', 'vision_model.vision_model.encoder.layers.9.self_attn.v_proj.weight', 'vision_model.vision_model.post_layernorm.bias', 'vision_model.vision_model.post_layernorm.weight', 'vision_model.vision_model.pre_layrnorm.bias', 'vision_model.vision_model.pre_layrnorm.weight', 'vision_model.visual_projection.weight']\n",
      "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n",
      "Some weights of InternVLChatModel were not initialized from the model checkpoint at OpenGVLab/InternVL2-4B and are newly initialized because the shapes did not match:\n",
      "- mlp1.0.bias: found shape torch.Size([4096]) in the checkpoint and torch.Size([512]) in the model instantiated\n",
      "- mlp1.0.weight: found shape torch.Size([4096]) in the checkpoint and torch.Size([512]) in the model instantiated\n",
      "- mlp1.1.weight: found shape torch.Size([3072, 4096]) in the checkpoint and torch.Size([3072, 512]) in the model instantiated\n",
      "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n",
      "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Sequential(\n",
      "  (0): LayerNorm((512,), eps=1e-05, elementwise_affine=True)\n",
      "  (1): Linear(in_features=512, out_features=3072, bias=True)\n",
      "  (2): GELU(approximate='none')\n",
      "  (3): Linear(in_features=3072, out_features=3072, bias=True)\n",
      ")\n",
      "Training: [Parameter containing:\n",
      "tensor([1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
      "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
      "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
      "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
      "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
      "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
      "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
      "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
      "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
      "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
      "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
      "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
      "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
      "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
      "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
      "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
      "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
      "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
      "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
      "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
      "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
      "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
      "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
      "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
      "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
      "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
      "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
      "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
      "        1., 1., 1., 1., 1., 1., 1., 1.], device='cuda:0', requires_grad=True), Parameter containing:\n",
      "tensor([0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
      "        0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
      "        0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
      "        0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
      "        0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
      "        0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
      "        0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
      "        0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
      "        0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
      "        0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
      "        0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
      "        0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
      "        0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
      "        0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
      "        0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
      "        0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
      "        0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
      "        0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
      "        0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
      "        0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
      "        0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
      "        0., 0., 0., 0., 0., 0., 0., 0.], device='cuda:0', requires_grad=True), Parameter containing:\n",
      "tensor([[ 0.0339,  0.0376,  0.0073,  ..., -0.0339,  0.0238,  0.0062],\n",
      "        [-0.0052, -0.0187,  0.0059,  ...,  0.0276, -0.0090,  0.0187],\n",
      "        [ 0.0234, -0.0322,  0.0179,  ..., -0.0114, -0.0010,  0.0280],\n",
      "        ...,\n",
      "        [ 0.0104, -0.0007,  0.0242,  ..., -0.0311, -0.0272,  0.0166],\n",
      "        [-0.0249, -0.0128,  0.0104,  ..., -0.0432, -0.0334,  0.0048],\n",
      "        [-0.0300, -0.0374,  0.0021,  ..., -0.0104,  0.0311,  0.0000]],\n",
      "       device='cuda:0', requires_grad=True), Parameter containing:\n",
      "tensor([-0.0425, -0.0312, -0.0302,  ..., -0.0107, -0.0334, -0.0184],\n",
      "       device='cuda:0', requires_grad=True), Parameter containing:\n",
      "tensor([[ 0.0349, -0.0058, -0.0051,  ..., -0.0162, -0.0181, -0.0238],\n",
      "        [-0.0034, -0.0095, -0.0264,  ..., -0.0123,  0.0048, -0.0051],\n",
      "        [-0.0266,  0.0070, -0.0043,  ...,  0.0015,  0.0116,  0.0056],\n",
      "        ...,\n",
      "        [-0.0108, -0.0024, -0.0011,  ...,  0.0107, -0.0093, -0.0156],\n",
      "        [-0.0225,  0.0118, -0.0011,  ...,  0.0048,  0.0154,  0.0074],\n",
      "        [-0.0044, -0.0165,  0.0197,  ...,  0.0096,  0.0107, -0.0024]],\n",
      "       device='cuda:0', requires_grad=True), Parameter containing:\n",
      "tensor([-0.0131,  0.0132, -0.0184,  ..., -0.0135, -0.0006,  0.0028],\n",
      "       device='cuda:0', requires_grad=True)]\n"
     ]
    }
   ],
   "source": [
    "\n",
    "%cd /home/ryn_mote/Misc/vlm_with_pooled_for_text_genrec/\n",
    "\n",
    "import numpy as np\n",
    "import torch\n",
    "import torchvision.transforms as T\n",
    "from PIL import Image\n",
    "from torchvision.transforms.functional import InterpolationMode\n",
    "from transformers import AutoModel, AutoTokenizer\n",
    "\n",
    "from model import model, tokenizer\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 243,
     "referenced_widgets": [
      "dda6bb6b93f446d59d72ff96ff7a853e",
      "b44eba0bbe4c43a1b0f721e678b4d283",
      "e437079090dc473982e44067232d5a8a",
      "c8e975345e394d50835853f171d168b5",
      "dce79a5e12054f3b81f81f75ae16e496",
      "0a1c58f845d8401f803dc82650ec5067",
      "be5c59d8ae394c148dcd0c6cf9103c6c",
      "851538e4adf34b9a923d109af48bf10f",
      "82f1095705fc42f1a0bd5c419efd5fb5",
      "1e8b80093b474466a159d263385af6c6",
      "bcd3745ef57746678408765d98eb4e05"
     ]
    },
    "id": "Fjz_CIWCgHIN",
    "outputId": "c64d772a-5df0-4f7e-e535-387777099423"
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "A3ep4uzx80DJ",
    "outputId": "012b5503-8950-4daf-b07f-cbf5c5da2e07"
   },
   "outputs": [],
   "source": [
    "\n",
    "from model import load_image\n",
    "\n",
    "# set the max number of tiles in `max_num`\n",
    "with torch.cuda.amp.autocast(True, torch.bfloat16):\n",
    "    pixel_values = load_image('/home/ryn_mote/Downloads/A polaroid of Silver Forgettings -- This flower does not exist.png', max_num=1).cuda()\n",
    "    emb1 = model.extract_feature(pixel_values.to(torch.bfloat16))\n",
    "\n",
    "    pixel_values = load_image('/home/ryn_mote/Downloads/20230707_160218.jpg', max_num=1).cuda()\n",
    "    emb2 = model.extract_feature(pixel_values.to(torch.bfloat16))\n",
    "\n",
    "    w = [3, 5]\n",
    "    embs = (emb1*w[0]+emb2*w[1]) / sum(w)\n",
    "\n",
    "    generation_config = dict(max_new_tokens=32, do_sample=False,)\n",
    "\n",
    "    # single-image single-round conversation (单图单轮对话)\n",
    "    question = '\\n '\n",
    "    response = model.chat(tokenizer, pixel_values, question, generation_config, visual_features=embs.to(torch.bfloat16))\n",
    "    print(f'User: {question}\\nAssistant: {response}')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "ncu5qq0wEfKN"
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "UgjhC95CDb26",
    "outputId": "709bb3ad-fe29-41a3-dd4d-d3bab9fb21ed"
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "accelerator": "GPU",
  "colab": {
   "gpuType": "A100",
   "machine_shape": "hm",
   "provenance": []
  },
  "kernelspec": {
   "display_name": "base",
   "language": "python",
   "name": "base"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.8"
  },
  "widgets": {
   "application/vnd.jupyter.widget-state+json": {
    "0a1c58f845d8401f803dc82650ec5067": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "1e8b80093b474466a159d263385af6c6": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "82f1095705fc42f1a0bd5c419efd5fb5": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "ProgressStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "ProgressStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "bar_color": null,
      "description_width": ""
     }
    },
    "851538e4adf34b9a923d109af48bf10f": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "b44eba0bbe4c43a1b0f721e678b4d283": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_0a1c58f845d8401f803dc82650ec5067",
      "placeholder": "​",
      "style": "IPY_MODEL_be5c59d8ae394c148dcd0c6cf9103c6c",
      "value": "Loading checkpoint shards: 100%"
     }
    },
    "bcd3745ef57746678408765d98eb4e05": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "be5c59d8ae394c148dcd0c6cf9103c6c": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "c8e975345e394d50835853f171d168b5": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_1e8b80093b474466a159d263385af6c6",
      "placeholder": "​",
      "style": "IPY_MODEL_bcd3745ef57746678408765d98eb4e05",
      "value": " 2/2 [00:00&lt;00:00,  4.98it/s]"
     }
    },
    "dce79a5e12054f3b81f81f75ae16e496": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "dda6bb6b93f446d59d72ff96ff7a853e": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HBoxModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HBoxModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HBoxView",
      "box_style": "",
      "children": [
       "IPY_MODEL_b44eba0bbe4c43a1b0f721e678b4d283",
       "IPY_MODEL_e437079090dc473982e44067232d5a8a",
       "IPY_MODEL_c8e975345e394d50835853f171d168b5"
      ],
      "layout": "IPY_MODEL_dce79a5e12054f3b81f81f75ae16e496"
     }
    },
    "e437079090dc473982e44067232d5a8a": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "FloatProgressModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "FloatProgressModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "ProgressView",
      "bar_style": "success",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_851538e4adf34b9a923d109af48bf10f",
      "max": 2,
      "min": 0,
      "orientation": "horizontal",
      "style": "IPY_MODEL_82f1095705fc42f1a0bd5c419efd5fb5",
      "value": 2
     }
    }
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}