diff --git "a/LLaVa_Med_Finteuning_VQA-RAD.ipynb" "b/LLaVa_Med_Finteuning_VQA-RAD.ipynb" new file mode 100644--- /dev/null +++ "b/LLaVa_Med_Finteuning_VQA-RAD.ipynb" @@ -0,0 +1,11888 @@ +{ + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "colab": { + "provenance": [], + "machine_shape": "hm", + "gpuType": "A100" + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + }, + "language_info": { + "name": "python" + }, + "widgets": { + "application/vnd.jupyter.widget-state+json": { + "642ebeffae584f5d919287d6b95c463e": { + "model_module": "@jupyter-widgets/controls", + "model_name": "VBoxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "VBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "VBoxView", + "box_style": "", + "children": [], + "layout": "IPY_MODEL_963c6db1116244c79f86386d28fd4eab" + } + }, + "0c359eca264c4fc381b8bcd7596a0b2e": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_d83e1a5c9752425399cf038ed5a8158d", + "placeholder": "", + "style": "IPY_MODEL_36c853e2257a4290875aff4ebc272875", + "value": "
Step | \n", + "Training Loss | \n", + "
---|---|
1793 | \n", + "1.067700 | \n", + "
3586 | \n", + "0.591500 | \n", + "
5379 | \n", + "0.442900 | \n", + "
7172 | \n", + "0.335300 | \n", + "
8965 | \n", + "0.246300 | \n", + "
" + ] + }, + "metadata": {} + }, + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "TrainOutput(global_step=8965, training_loss=0.5367301570724258, metrics={'train_runtime': 3522.3938, 'train_samples_per_second': 2.545, 'train_steps_per_second': 2.545, 'total_flos': 1.058735921163264e+16, 'train_loss': 0.5367301570724258, 'epoch': 5.0})" + ] + }, + "metadata": {}, + "execution_count": 13 + } + ] + }, + { + "cell_type": "code", + "source": [ + "from transformers import AutoModelForCausalLM\n", + "from peft import PeftModel\n", + "\n", + "trainer.save_model('lora_trained_model')\n", + "base_model = AutoModelForCausalLM.from_pretrained('microsoft/llava-med-v1.5-mistral-7b')\n", + "\n", + "trained_model = PeftModel.from_pretrained(base_model, 'lora_trained_model')\n", + "merged_trained_model = trained_model.merge_and_unload()\n", + "merged_trained_model.save_pretrained('merged_trained_model', push_to_hub=True, repo_id=\"Veda0718/llava-med-v1.5-mistral-7b-finetuned\")\n", + "\n", + "tokenizer.save_pretrained('merged_trained_model', push_to_hub=True, repo_id='Veda0718/llava-med-v1.5-mistral-7b-finetuned')" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 464, + "referenced_widgets": [ + "e9c208a206f24f41ab517a22259decc7", + "da3f1c66795542e6a48d45f83dfe5802", + "1d13c2b5914c4c409122009752dec4f4", + "83ddf9a7155a4279af93abc698f0a5b2", + "94c6a199dee84e288cb99bc980e93c9a", + "83c695813fa542ce8ad169cba4fd8e2f", + "f3f21c447a4d4802a9f49e65c7c480dd", + "ecb4aea597bd42708c495cc3f2e79b1e", + "221b8cf7d49a41a5ba158b301b899e6e", + "27b5d4d17b654e5e86a78442c05c9a88", + "efdfb9f4ace34fadae817f94941f7fdd", + "0190b10bcc8b481bb892e781b06ae9dc", + "fd1b77528888424d9580b063bde4d073", + "2766a8bd64c44f2cb49b15b74e677237", + "359650fa2a964ba5911691a82acea39a", + "69af897208b443f08f2c5b6672511119", + "9ee446d6b67341d993058763e825f1de", + "6c458ae807f04feea1089ca476b48b0f", + "4bc31bef8b4a46819f1292e432105fc9", + "2079fd941f514c4aa5c76868544ed4ac", + "e05b8b3f2cc7428db18db22c78c80540", + "bdb58d3bfa1d46ab9f3bfe9a0dddf316", + "58740980c0624a75bbe19267d8006837", + "ee8726bd6af74b11905c3b9fb066b05a", + "b8794d76659245ac81e3ef9c6c0a9d11", + "6d1f2fe0a6c84e5388a776dc2373f23f", + "37f46e5e4cdf4e16a2cfb2e77a265976", + "586ea56cdeae4810aad37803a12785d1", + "ff274f10ceec4d76a5c7e2911dd367b4", + "6652e74261ba4ff7bcd5f9367ed1bee7", + "329e63933f264130bca60cafb1affff0", + "059133458396444aa86e6bf5face2a9c", + "5be035e66cb5417e88ce9a30d9b67a40", + "1c598733246a45edb3208a10f853dce0", + "a5247c199d4543179891e6d0bb7f45a4", + "d0018ec5cd174e499f9464c098cd7bba", + "c5dd891975214566ad178a2251d45771", + "22f69ae6c5a242519a9c90e0bcbd0166", + "d6b10a51578545f6ba0002d8aff2a377", + "053e3972930c464485a564eb2f147cb8", + "5a5e11e02bf341baa77ee4ea703d7a74", + "84f11b3f7cc8461aa1fa7781cb2a987e", + "828345fa67c942c9b7901658ef8a5716", + "a177c5eb1d41461eb61b08b40e05ff80", + "beda9ae8817f4bee928c811284cd06dc", + "28464de7dafc4874b5eca124ed03719b", + "f9948434e1e44fbdb659e92379a3c99a", + "c8a141cf57c843e18cb9ef6695db1324", + "7bb96716ab0d46a787595c39af19e4d3", + "41eb10712cee490899a34b3cd652f9cd", + "a0d07c187c0747dea45dbd1e4c5982cf", + "5ed2c17abf974fa987ddca58917987f6", + "bbd5ee43d9ce4de0afc03a21fb7a89b6", + "2130746f9e9e431aa3d62b237a79b09e", + "d60aef286d7046fab2acea365bd7be7d", + "aa51163cebaf412d8c19a89e7c697edc", + "295e97a8c5e54863818bf117c8fcd03b", + "8645b216ca38498b86aeca0d9a526731", + "5b1edd4c121041d3a4fbcc2cc9c16812", + "21db273510374a25a6f75017a79b7258", + "810876c404ab480aa3639f547ee27391", + "9909dfd4ff014cfd897dddda3a6f7650", + "54553703aa7c4607915b6b11772cdb90", + "6886ab716bd24f759a7adb2212c62358", + "ff0d4d03f2db4247bad97ba47f79d5fb", + "9cbadd9a5e59416690fc55e92636dda0", + "6a295e31257b43d0989bbee57ade4be1", + "93752412635c4f1380a937e1909077c5", + "414e653d5d8344a68ccbfbd6e5b63d79", + "f97542ccca154fe3b061f0b44815ebe2", + "7b1089aafe93410caee89a8b20799981", + "9ddb6b8ba699470cb3f09169568353f6", + "70c1f5f14e8e48fcbd2ca6d2b4b74a81", + "f4330e2ddb7b487cad95aa25f333d8ec", + "cf6f52c4b692451aba489b18631f16b1", + "7d4b66df732944eda7d7f83fcf3fd6b4", + "37139700549b4bfcb6a1f7e9f89b6b00", + "c6ae4f34e7a94795a35af7ee05548840", + "705cc368a70d4d3db2d1decfa7973da6", + "82a20e7e19234028bc543b057289c604", + "421206810cb245418542d158be0d5df5", + "b634046155fa4a4aa93e6fb13ea0169b", + "c1990a0d240e480694e6dbb296926cd0", + "8692566ca2724010b9a4f3815fc12eee", + "13cab992818b463faeacde56bfb51eb8", + "6240e92292f54fc5aaa026d2c9ead471", + "666616c2f51b451c99ddc2c3ef0ace47", + "aae5d7aa8ddb48ebbfaae2f6df81d3c4", + "cb2726902fbe432ba5e6373074040875", + "a87ecfe7ca834f7d8d5754454d7e22fd", + "d200ad3496e74c858a2dd284304f19e0", + "4dba8cf1e142426b855c66977bfc59f9", + "2e5872d30ef14b01ac444fef6ec31a53", + "4d9a6fe111494077a4a4110e8da0bf96", + "ea6a8bf8dab049cda53007709b51e2cc", + "180888109281453095d327f624508400", + "b055fde04b26475f8439e973b5c954f5", + "2d22dce3bbb94201a093df82214dd128", + "2aafe63502894ea48871652d8fbfef94" + ] + }, + "id": "6nB_NiP9O0tI", + "outputId": "9c95083e-49fa-47ad-9c42-5bb65882c670" + }, + "execution_count": 14, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "Loading checkpoint shards: 0%| | 0/4 [00:00, ?it/s]" + ], + "application/vnd.jupyter.widget-view+json": { + "version_major": 2, + "version_minor": 0, + "model_id": "e9c208a206f24f41ab517a22259decc7" + } + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stderr", + "text": [ + "Some weights of the model checkpoint at microsoft/llava-med-v1.5-mistral-7b were not used when initializing LlavaMistralForCausalLM: ['model.vision_tower.vision_tower.vision_model.embeddings.class_embedding', 'model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight', 'model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.post_layernorm.bias', 'model.vision_tower.vision_tower.vision_model.post_layernorm.weight', 'model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias', 'model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight']\n", + "- This IS expected if you are initializing LlavaMistralForCausalLM 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 LlavaMistralForCausalLM from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "model-00004-of-00006.safetensors: 0%| | 0.00/5.00G [00:00, ?B/s]" + ], + "application/vnd.jupyter.widget-view+json": { + "version_major": 2, + "version_minor": 0, + "model_id": "0190b10bcc8b481bb892e781b06ae9dc" + } + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "model-00005-of-00006.safetensors: 0%| | 0.00/4.83G [00:00, ?B/s]" + ], + "application/vnd.jupyter.widget-view+json": { + "version_major": 2, + "version_minor": 0, + "model_id": "58740980c0624a75bbe19267d8006837" + } + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "model-00001-of-00006.safetensors: 0%| | 0.00/4.99G [00:00, ?B/s]" + ], + "application/vnd.jupyter.widget-view+json": { + "version_major": 2, + "version_minor": 0, + "model_id": "1c598733246a45edb3208a10f853dce0" + } + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "model-00003-of-00006.safetensors: 0%| | 0.00/5.00G [00:00, ?B/s]" + ], + "application/vnd.jupyter.widget-view+json": { + "version_major": 2, + "version_minor": 0, + "model_id": "beda9ae8817f4bee928c811284cd06dc" + } + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "model-00006-of-00006.safetensors: 0%| | 0.00/4.33G [00:00, ?B/s]" + ], + "application/vnd.jupyter.widget-view+json": { + "version_major": 2, + "version_minor": 0, + "model_id": "aa51163cebaf412d8c19a89e7c697edc" + } + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "Upload 6 LFS files: 0%| | 0/6 [00:00, ?it/s]" + ], + "application/vnd.jupyter.widget-view+json": { + "version_major": 2, + "version_minor": 0, + "model_id": "6a295e31257b43d0989bbee57ade4be1" + } + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "model-00002-of-00006.safetensors: 0%| | 0.00/4.90G [00:00, ?B/s]" + ], + "application/vnd.jupyter.widget-view+json": { + "version_major": 2, + "version_minor": 0, + "model_id": "c6ae4f34e7a94795a35af7ee05548840" + } + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "tokenizer.model: 0%| | 0.00/493k [00:00, ?B/s]" + ], + "application/vnd.jupyter.widget-view+json": { + "version_major": 2, + "version_minor": 0, + "model_id": "cb2726902fbe432ba5e6373074040875" + } + }, + "metadata": {} + }, + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "('merged_trained_model/tokenizer_config.json',\n", + " 'merged_trained_model/special_tokens_map.json',\n", + " 'merged_trained_model/tokenizer.model',\n", + " 'merged_trained_model/added_tokens.json',\n", + " 'merged_trained_model/tokenizer.json')" + ] + }, + "metadata": {}, + "execution_count": 14 + } + ] + }, + { + "cell_type": "code", + "source": [ + "# trainer.model.save_pretrained(\"/content/drive/MyDrive/trained_modelss\")" + ], + "metadata": { + "id": "SltCH5SYlagW" + }, + "execution_count": null, + "outputs": [] + } + ] +} \ No newline at end of file