diff --git "a/notebooks/test_model.ipynb" "b/notebooks/test_model.ipynb" --- "a/notebooks/test_model.ipynb" +++ "b/notebooks/test_model.ipynb" @@ -10,7 +10,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "id": "6c7800a6", "metadata": {}, "outputs": [], @@ -27,7 +27,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 2, "id": "b447e2c4", "metadata": {}, "outputs": [], @@ -39,7 +39,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "id": "c2fc0e7a", "metadata": {}, "outputs": [], @@ -55,7 +55,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "id": "b294a94a", "metadata": {}, "outputs": [], @@ -82,7 +82,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "id": "97f24046", "metadata": {}, "outputs": [], @@ -98,10 +98,61 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 11, + "id": "88bebba3", + "metadata": {}, + "outputs": [ + { + "ename": "AttributeError", + "evalue": "'AudioDiffusion' object has no attribute 'Mel'", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mAttributeError\u001b[0m Traceback (most recent call last)", + "Input \u001b[0;32mIn [11]\u001b[0m, in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43maudio_diffusion\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mMel\u001b[49m\n", + "\u001b[0;31mAttributeError\u001b[0m: 'AudioDiffusion' object has no attribute 'Mel'" + ] + } + ], + "source": [ + "audio_diffusion.Mel" + ] + }, + { + "cell_type": "code", + "execution_count": 6, "id": "a3d45c36", "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "89e8b4345bab47378576244f4d3f7b44", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + "Downloading: 0%| | 0.00/244 [00:00" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "\n", + " \n", + " " + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "\n", + " \n", + " " + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Seed = 2275699277188148\n" + ] + }, + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "e049bd4fb00542feba252d9f9da2334d", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + " 0%| | 0/1000 [00:00\u001b[0;34m()\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mSeed = \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mseed\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m 4\u001b[0m generator\u001b[38;5;241m.\u001b[39mmanual_seed(seed)\n\u001b[1;32m 5\u001b[0m image, (sample_rate,\n\u001b[0;32m----> 6\u001b[0m audio) \u001b[38;5;241m=\u001b[39m \u001b[43maudio_diffusion\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate_spectrogram_and_audio\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 7\u001b[0m \u001b[43m \u001b[49m\u001b[43mgenerator\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mgenerator\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 8\u001b[0m display(image)\n\u001b[1;32m 9\u001b[0m display(Audio(audio, rate\u001b[38;5;241m=\u001b[39msample_rate))\n", + "File \u001b[0;32m~/ML/huggingface/audio-diffusion/audiodiffusion/__init__.py:54\u001b[0m, in \u001b[0;36mAudioDiffusion.generate_spectrogram_and_audio\u001b[0;34m(self, steps, generator, step_generator, eta, noise)\u001b[0m\n\u001b[1;32m 32\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mgenerate_spectrogram_and_audio\u001b[39m(\n\u001b[1;32m 33\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 34\u001b[0m steps: \u001b[38;5;28mint\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 38\u001b[0m noise: torch\u001b[38;5;241m.\u001b[39mTensor \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 39\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Tuple[Image\u001b[38;5;241m.\u001b[39mImage, Tuple[\u001b[38;5;28mint\u001b[39m, np\u001b[38;5;241m.\u001b[39mndarray]]:\n\u001b[1;32m 40\u001b[0m \u001b[38;5;124;03m\"\"\"Generate random mel spectrogram and convert to audio.\u001b[39;00m\n\u001b[1;32m 41\u001b[0m \n\u001b[1;32m 42\u001b[0m \u001b[38;5;124;03m Args:\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 51\u001b[0m \u001b[38;5;124;03m (float, np.ndarray): sample rate and raw audio\u001b[39;00m\n\u001b[1;32m 52\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[1;32m 53\u001b[0m images, (sample_rate,\n\u001b[0;32m---> 54\u001b[0m audios) \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpipe\u001b[49m\u001b[43m(\u001b[49m\u001b[43mbatch_size\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 55\u001b[0m \u001b[43m \u001b[49m\u001b[43msteps\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msteps\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 56\u001b[0m \u001b[43m \u001b[49m\u001b[43mgenerator\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mgenerator\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 57\u001b[0m \u001b[43m \u001b[49m\u001b[43mstep_generator\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstep_generator\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 58\u001b[0m \u001b[43m \u001b[49m\u001b[43meta\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43meta\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 59\u001b[0m \u001b[43m \u001b[49m\u001b[43mnoise\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mnoise\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 60\u001b[0m \u001b[43m \u001b[49m\u001b[43mreturn_dict\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m)\u001b[49m\n\u001b[1;32m 61\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m images[\u001b[38;5;241m0\u001b[39m], (sample_rate, audios[\u001b[38;5;241m0\u001b[39m])\n", + "File \u001b[0;32m~/.local/share/virtualenvs/huggingface-OfWfm_Zx/lib/python3.10/site-packages/torch/autograd/grad_mode.py:27\u001b[0m, in \u001b[0;36m_DecoratorContextManager.__call__..decorate_context\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 24\u001b[0m \u001b[38;5;129m@functools\u001b[39m\u001b[38;5;241m.\u001b[39mwraps(func)\n\u001b[1;32m 25\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdecorate_context\u001b[39m(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m 26\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mclone():\n\u001b[0;32m---> 27\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", + "File \u001b[0;32m~/ML/huggingface/diffusers/src/diffusers/pipelines/audio_diffusion/pipeline_audio_diffusion.py:160\u001b[0m, in \u001b[0;36mAudioDiffusionPipeline.__call__\u001b[0;34m(self, batch_size, audio_file, raw_audio, slice, start_step, steps, generator, mask_start_secs, mask_end_secs, step_generator, eta, noise, return_dict)\u001b[0m\n\u001b[1;32m 157\u001b[0m mask \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mscheduler\u001b[38;5;241m.\u001b[39madd_noise(input_images, noise, torch\u001b[38;5;241m.\u001b[39mtensor(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mscheduler\u001b[38;5;241m.\u001b[39mtimesteps[start_step:]))\n\u001b[1;32m 159\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m step, t \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28menumerate\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mprogress_bar(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mscheduler\u001b[38;5;241m.\u001b[39mtimesteps[start_step:])):\n\u001b[0;32m--> 160\u001b[0m model_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43munet\u001b[49m\u001b[43m(\u001b[49m\u001b[43mimages\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mt\u001b[49m\u001b[43m)\u001b[49m[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msample\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n\u001b[1;32m 162\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mscheduler, DDIMScheduler):\n\u001b[1;32m 163\u001b[0m images \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mscheduler\u001b[38;5;241m.\u001b[39mstep(\n\u001b[1;32m 164\u001b[0m model_output\u001b[38;5;241m=\u001b[39mmodel_output, timestep\u001b[38;5;241m=\u001b[39mt, sample\u001b[38;5;241m=\u001b[39mimages, eta\u001b[38;5;241m=\u001b[39meta, generator\u001b[38;5;241m=\u001b[39mstep_generator\n\u001b[1;32m 165\u001b[0m )[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mprev_sample\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n", + "File \u001b[0;32m~/.local/share/virtualenvs/huggingface-OfWfm_Zx/lib/python3.10/site-packages/torch/nn/modules/module.py:1130\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *input, **kwargs)\u001b[0m\n\u001b[1;32m 1126\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m 1127\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m 1128\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m 1129\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1130\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1131\u001b[0m \u001b[38;5;66;03m# Do not call functions when jit is used\u001b[39;00m\n\u001b[1;32m 1132\u001b[0m full_backward_hooks, non_full_backward_hooks \u001b[38;5;241m=\u001b[39m [], []\n", + "File \u001b[0;32m~/ML/huggingface/diffusers/src/diffusers/models/unet_2d.py:247\u001b[0m, in \u001b[0;36mUNet2DModel.forward\u001b[0;34m(self, sample, timestep, return_dict)\u001b[0m\n\u001b[1;32m 245\u001b[0m sample, skip_sample \u001b[38;5;241m=\u001b[39m upsample_block(sample, res_samples, emb, skip_sample)\n\u001b[1;32m 246\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 247\u001b[0m sample \u001b[38;5;241m=\u001b[39m \u001b[43mupsample_block\u001b[49m\u001b[43m(\u001b[49m\u001b[43msample\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mres_samples\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43memb\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 249\u001b[0m \u001b[38;5;66;03m# 6. post-process\u001b[39;00m\n\u001b[1;32m 250\u001b[0m sample \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconv_norm_out(sample)\n", + "File \u001b[0;32m~/.local/share/virtualenvs/huggingface-OfWfm_Zx/lib/python3.10/site-packages/torch/nn/modules/module.py:1130\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *input, **kwargs)\u001b[0m\n\u001b[1;32m 1126\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m 1127\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m 1128\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m 1129\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1130\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1131\u001b[0m \u001b[38;5;66;03m# Do not call functions when jit is used\u001b[39;00m\n\u001b[1;32m 1132\u001b[0m full_backward_hooks, non_full_backward_hooks \u001b[38;5;241m=\u001b[39m [], []\n", + "File \u001b[0;32m~/ML/huggingface/diffusers/src/diffusers/models/unet_2d_blocks.py:1317\u001b[0m, in \u001b[0;36mUpBlock2D.forward\u001b[0;34m(self, hidden_states, res_hidden_states_tuple, temb, upsample_size)\u001b[0m\n\u001b[1;32m 1315\u001b[0m hidden_states \u001b[38;5;241m=\u001b[39m torch\u001b[38;5;241m.\u001b[39mutils\u001b[38;5;241m.\u001b[39mcheckpoint\u001b[38;5;241m.\u001b[39mcheckpoint(create_custom_forward(resnet), hidden_states, temb)\n\u001b[1;32m 1316\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1317\u001b[0m hidden_states \u001b[38;5;241m=\u001b[39m \u001b[43mresnet\u001b[49m\u001b[43m(\u001b[49m\u001b[43mhidden_states\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtemb\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1319\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mupsamplers \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 1320\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m upsampler \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mupsamplers:\n", + "File \u001b[0;32m~/.local/share/virtualenvs/huggingface-OfWfm_Zx/lib/python3.10/site-packages/torch/nn/modules/module.py:1130\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *input, **kwargs)\u001b[0m\n\u001b[1;32m 1126\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m 1127\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m 1128\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m 1129\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1130\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1131\u001b[0m \u001b[38;5;66;03m# Do not call functions when jit is used\u001b[39;00m\n\u001b[1;32m 1132\u001b[0m full_backward_hooks, non_full_backward_hooks \u001b[38;5;241m=\u001b[39m [], []\n", + "File \u001b[0;32m~/ML/huggingface/diffusers/src/diffusers/models/resnet.py:467\u001b[0m, in \u001b[0;36mResnetBlock2D.forward\u001b[0;34m(self, input_tensor, temb)\u001b[0m\n\u001b[1;32m 464\u001b[0m hidden_states \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconv1(hidden_states)\n\u001b[1;32m 466\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m temb \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m--> 467\u001b[0m temb \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtime_emb_proj\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mnonlinearity\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtemb\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m[:, :, \u001b[38;5;28;01mNone\u001b[39;00m, \u001b[38;5;28;01mNone\u001b[39;00m]\n\u001b[1;32m 468\u001b[0m hidden_states \u001b[38;5;241m=\u001b[39m hidden_states \u001b[38;5;241m+\u001b[39m temb\n\u001b[1;32m 470\u001b[0m hidden_states \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mnorm2(hidden_states)\n", + "File \u001b[0;32m~/.local/share/virtualenvs/huggingface-OfWfm_Zx/lib/python3.10/site-packages/torch/nn/modules/module.py:1130\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *input, **kwargs)\u001b[0m\n\u001b[1;32m 1126\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m 1127\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m 1128\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m 1129\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1130\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1131\u001b[0m \u001b[38;5;66;03m# Do not call functions when jit is used\u001b[39;00m\n\u001b[1;32m 1132\u001b[0m full_backward_hooks, non_full_backward_hooks \u001b[38;5;241m=\u001b[39m [], []\n", + "File \u001b[0;32m~/.local/share/virtualenvs/huggingface-OfWfm_Zx/lib/python3.10/site-packages/torch/nn/modules/linear.py:114\u001b[0m, in \u001b[0;36mLinear.forward\u001b[0;34m(self, input)\u001b[0m\n\u001b[1;32m 113\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;28minput\u001b[39m: Tensor) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Tensor:\n\u001b[0;32m--> 114\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m F\u001b[38;5;241m.\u001b[39mlinear(\u001b[38;5;28minput\u001b[39m, \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mweight\u001b[49m, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbias)\n", + "File \u001b[0;32m~/.local/share/virtualenvs/huggingface-OfWfm_Zx/lib/python3.10/site-packages/torch/nn/modules/module.py:1194\u001b[0m, in \u001b[0;36mModule.__getattr__\u001b[0;34m(self, name)\u001b[0m\n\u001b[1;32m 1191\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m_is_full_backward_hook\u001b[39m\u001b[38;5;124m'\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__dict__\u001b[39m:\n\u001b[1;32m 1192\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_is_full_backward_hook \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m-> 1194\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__getattr__\u001b[39m(\u001b[38;5;28mself\u001b[39m, name: \u001b[38;5;28mstr\u001b[39m) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Union[Tensor, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mModule\u001b[39m\u001b[38;5;124m'\u001b[39m]:\n\u001b[1;32m 1195\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m_parameters\u001b[39m\u001b[38;5;124m'\u001b[39m \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__dict__\u001b[39m:\n\u001b[1;32m 1196\u001b[0m _parameters \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__dict__\u001b[39m[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m_parameters\u001b[39m\u001b[38;5;124m'\u001b[39m]\n", + "\u001b[0;31mKeyboardInterrupt\u001b[0m: " + ] + } + ], "source": [ "for _ in range(10):\n", " seed = generator.seed()\n",