tidied up the code

Gemma2_2B/inference.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -17,92 +17,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "d00ec085003e409d906784abc1f89dc1",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "config.json:   0%|          | 0.00/838 [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "f:\\TADBot\\.venv\\Lib\\site-packages\\huggingface_hub\\file_download.py:139: UserWarning: `huggingface_hub` cache-system uses symlinks by default to efficiently store duplicated files but your machine does not support them in F:\\TADBot\\Gemma2_2B\\.cache\\models--google--gemma-2-2b-it. Caching files will still work but in a degraded version that might require more space on your disk. This warning can be disabled by setting the `HF_HUB_DISABLE_SYMLINKS_WARNING` environment variable. For more details, see https://huggingface.co/docs/huggingface_hub/how-to-cache#limitations.\n",
-      "To support symlinks on Windows, you either need to activate Developer Mode or to run Python as an administrator. In order to activate developer mode, see this article: https://docs.microsoft.com/en-us/windows/apps/get-started/enable-your-device-for-development\n",
-      "  warnings.warn(message)\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "bdee67c51d7547a48e45f17db7fb3734",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "model.safetensors.index.json:   0%|          | 0.00/24.2k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "ad86eff32cc1447486e69c5f5f90e4a4",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "78cab016a2d54731a94ef45e85d65ddd",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "model-00001-of-00002.safetensors:   0%|          | 0.00/4.99G [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "52b50ff81d0d481ab475878606935162",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "model-00002-of-00002.safetensors:   0%|          | 0.00/241M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "7dfed61b7e0a4338aee7ad14df4d85ca",
+       "model_id": "6124a76f904b49be930009acef84305b",
        "version_major": 2,
        "version_minor": 0
       },
@@ -112,88 +33,18 @@
      },
      "metadata": {},
      "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "9ac1e6a0b72a44d3a8a648bce2138c3d",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "generation_config.json:   0%|          | 0.00/187 [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "f0129c204a454f22968aebe59b75ea1a",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "tokenizer_config.json:   0%|          | 0.00/47.0k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "ca55b303b11347cbbf5970327d2d8a82",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "tokenizer.model:   0%|          | 0.00/4.24M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "33601521ca8544e7a98c88506257dd20",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "tokenizer.json:   0%|          | 0.00/17.5M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "f353232bbf6b4da3ac62e02fa7f58990",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "special_tokens_map.json:   0%|          | 0.00/636 [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
     }
    ],
    "source": [
     "from transformers import AutoTokenizer, AutoModelForCausalLM\n",
     "model_name = \"google/gemma-2-2b-it\"\n",
-    "model = AutoModelForCausalLM.from_pretrained(model_name, device_map=\"auto\", cache_dir=\".cache/\")\n",
+    "model = AutoModelForCausalLM.from_pretrained(model_name, cache_dir=\".cache/\")\n",
     "tokenizer = AutoTokenizer.from_pretrained(model_name, cache_dir=\".cache/\")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
@@ -237,44 +88,27 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "<bos>What should I do on a trip to Europe?\n",
-      "\n",
-      "That's a great question!  To give you the best advice, I need a little more information. Tell me about:\n",
-      "\n",
-      "**1. Your Interests:** \n",
-      "   * What kind of things do you enjoy doing? (History, art, food, nightlife, nature, adventure, relaxation, etc.)\n",
-      "   * Are there any specific places or activities you've always wanted to experience?\n",
-      "\n",
-      "**2. Your Travel Style:**\n",
-      "   * Do you prefer to travel on your own, with a partner, or with a group?\n",
-      "   * Do you like to plan everything in advance or be more spontaneous?\n",
-      "   * What's your budget like?\n",
-      "\n",
-      "**3. Your Trip Details:**\n",
-      "   * How long will you be traveling for?\n",
-      "   * What time of year are you planning to go?\n",
-      "   * Do you have any specific destinations in mind?\n",
+      "<bos>I have so many issues to address. I have a history of sexual abuse, I’m a breast cancer survivor and I am a lifetime insomniac.    I have a long history of depression and I’m beginning to have anxiety. I have low self esteem but I’ve been happily married for almost 35 years.I’ve never had counseling about any of this. Do I have too many issues to address in counseling?\n",
       "\n",
-      "Once I have this information, I can give you personalized recommendations for your European adventure! \n",
-      "<end_of_turn>\n",
-      "CPU times: total: 7.23 s\n",
-      "Wall time: 7.56 s\n"
+      "It's wonderful that you're recognizing the need for support and seeking help. You absolutely do not have too many issues to address in counseling. In fact, it's\n",
+      "CPU times: total: 28.8 s\n",
+      "Wall time: 20.3 s\n"
      ]
     }
    ],
    "source": [
     "%%time\n",
-    "input_text = \"What should I do on a trip to Europe?\"\n",
+    "input_text = \"I have so many issues to address. I have a history of sexual abuse, I’m a breast cancer survivor and I am a lifetime insomniac.    I have a long history of depression and I’m beginning to have anxiety. I have low self esteem but I’ve been happily married for almost 35 years.I’ve never had counseling about any of this. Do I have too many issues to address in counseling?\"\n",
     "\n",
-    "input_ids = tokenizer(input_text, return_tensors=\"pt\").to(\"cuda\")\n",
-    "outputs = model.generate(**input_ids, max_length=2048)\n",
+    "input_ids = tokenizer(input_text, return_tensors=\"pt\")\n",
+    "outputs = model.generate(**input_ids, max_length=128)\n",
     "print(tokenizer.decode(outputs[0]))"
    ]
   },
@@ -287,7 +121,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -303,13 +137,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "21f72716997c42cfa2244677b36b85f8",
+       "model_id": "7e7639d5cbc748f189f84f0287700585",
        "version_major": 2,
        "version_minor": 0
       },
@@ -323,12 +157,12 @@
     {
      "data": {
       "text/plain": [
-       "('gemma2-TADBot\\\\tokenizer_config.json',\n",
-       " 'gemma2-TADBot\\\\special_tokens_map.json',\n",
-       " 'gemma2-TADBot\\\\tokenizer.json')"
+       "('gemma-2-2b-it-therapist\\\\tokenizer_config.json',\n",
+       " 'gemma-2-2b-it-therapist\\\\special_tokens_map.json',\n",
+       " 'gemma-2-2b-it-therapist\\\\tokenizer.json')"
       ]
      },
-     "execution_count": 2,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -344,38 +178,55 @@
     ")\n",
     "model = PeftModel.from_pretrained(base_model, new_model, cache_dir = \".cache/\")\n",
     "model = model.merge_and_unload()\n",
-    "model.save_pretrained(\"gemma2-TADBot\")\n",
     "\n",
     "# Reload tokenizer to save it\n",
-    "tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True, cache_dir = \".cache/\")\n",
-    "tokenizer.pad_token = tokenizer.eos_token\n",
-    "tokenizer.padding_side = \"right\"\n",
-    "tokenizer.save_pretrained(\"gemma2-TADBot\")"
+    "tokenizer = AutoTokenizer.from_pretrained(\n",
+    "    model_name, trust_remote_code=True, cache_dir=\".cache/\"\n",
+    ")\n",
+    "tokenizer.save_pretrained(\"gemma-2-2b-it-therapist\")\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
-     "name": "stdout",
+     "name": "stderr",
      "output_type": "stream",
      "text": [
-      "<bos>I have so many issues to address. I have a history of sexual abuse, I’m a breast cancer survivor and I am a lifetime insomniac.    I have a long history of depression and I’m beginning to have anxiety. I have low self esteem but I’ve been happily married for almost 35 years.I’ve never had counseling about any of this. Do I have too many issues to address in counseling?\n",
-      "\n",
-      "### Response:\n",
-      "I would say absolutely not!  It is never too many issues to address in counseling.  It is actually quite common for people to come into therapy with a lot of issues and it is often the case that the issues are interconnected.  For example, a person who has experienced trauma may have difficulty sleeping, have low self esteem, and have anxiety.  It is important to remember that counseling is a collaborative process and the therapist will work with you to help you address all of your issues.\n",
-      "<eos>\n",
-      "CPU times: total: 16 s\n",
-      "Wall time: 17.3 s\n"
+      "f:\\TADBot\\.venv\\Lib\\site-packages\\transformers\\generation\\utils.py:2097: UserWarning: You are calling .generate() with the `input_ids` being on a device type different than your model's device. `input_ids` is on cuda, whereas the model is on cpu. You may experience unexpected behaviors or slower generation. Please make sure that you have put `input_ids` to the correct device by calling for example input_ids = input_ids.to('cpu') before running `.generate()`.\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "ename": "RuntimeError",
+     "evalue": "Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument index in method wrapper_CUDA__index_select)",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mRuntimeError\u001b[0m                              Traceback (most recent call last)",
+      "File \u001b[1;32m<timed exec>:2\u001b[0m\n",
+      "File \u001b[1;32mf:\\TADBot\\.venv\\Lib\\site-packages\\torch\\utils\\_contextlib.py:116\u001b[0m, in \u001b[0;36mcontext_decorator.<locals>.decorate_context\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m    113\u001b[0m \u001b[38;5;129m@functools\u001b[39m\u001b[38;5;241m.\u001b[39mwraps(func)\n\u001b[0;32m    114\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[0;32m    115\u001b[0m     \u001b[38;5;28;01mwith\u001b[39;00m ctx_factory():\n\u001b[1;32m--> 116\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[1;32mf:\\TADBot\\.venv\\Lib\\site-packages\\transformers\\generation\\utils.py:2215\u001b[0m, in \u001b[0;36mGenerationMixin.generate\u001b[1;34m(self, inputs, generation_config, logits_processor, stopping_criteria, prefix_allowed_tokens_fn, synced_gpus, assistant_model, streamer, negative_prompt_ids, negative_prompt_attention_mask, **kwargs)\u001b[0m\n\u001b[0;32m   2207\u001b[0m     input_ids, model_kwargs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_expand_inputs_for_generation(\n\u001b[0;32m   2208\u001b[0m         input_ids\u001b[38;5;241m=\u001b[39minput_ids,\n\u001b[0;32m   2209\u001b[0m         expand_size\u001b[38;5;241m=\u001b[39mgeneration_config\u001b[38;5;241m.\u001b[39mnum_return_sequences,\n\u001b[0;32m   2210\u001b[0m         is_encoder_decoder\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconfig\u001b[38;5;241m.\u001b[39mis_encoder_decoder,\n\u001b[0;32m   2211\u001b[0m         \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mmodel_kwargs,\n\u001b[0;32m   2212\u001b[0m     )\n\u001b[0;32m   2214\u001b[0m     \u001b[38;5;66;03m# 12. run sample (it degenerates to greedy search when `generation_config.do_sample=False`)\u001b[39;00m\n\u001b[1;32m-> 2215\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_sample\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m   2216\u001b[0m \u001b[43m        \u001b[49m\u001b[43minput_ids\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   2217\u001b[0m \u001b[43m        \u001b[49m\u001b[43mlogits_processor\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mprepared_logits_processor\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   2218\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstopping_criteria\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mprepared_stopping_criteria\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   2219\u001b[0m \u001b[43m        \u001b[49m\u001b[43mgeneration_config\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mgeneration_config\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   2220\u001b[0m \u001b[43m        \u001b[49m\u001b[43msynced_gpus\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msynced_gpus\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   2221\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstreamer\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstreamer\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   2222\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mmodel_kwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   2223\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   2225\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m generation_mode \u001b[38;5;129;01min\u001b[39;00m (GenerationMode\u001b[38;5;241m.\u001b[39mBEAM_SAMPLE, GenerationMode\u001b[38;5;241m.\u001b[39mBEAM_SEARCH):\n\u001b[0;32m   2226\u001b[0m     \u001b[38;5;66;03m# 11. prepare beam search scorer\u001b[39;00m\n\u001b[0;32m   2227\u001b[0m     beam_scorer \u001b[38;5;241m=\u001b[39m BeamSearchScorer(\n\u001b[0;32m   2228\u001b[0m         batch_size\u001b[38;5;241m=\u001b[39mbatch_size,\n\u001b[0;32m   2229\u001b[0m         num_beams\u001b[38;5;241m=\u001b[39mgeneration_config\u001b[38;5;241m.\u001b[39mnum_beams,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m   2234\u001b[0m         max_length\u001b[38;5;241m=\u001b[39mgeneration_config\u001b[38;5;241m.\u001b[39mmax_length,\n\u001b[0;32m   2235\u001b[0m     )\n",
+      "File \u001b[1;32mf:\\TADBot\\.venv\\Lib\\site-packages\\transformers\\generation\\utils.py:3206\u001b[0m, in \u001b[0;36mGenerationMixin._sample\u001b[1;34m(self, input_ids, logits_processor, stopping_criteria, generation_config, synced_gpus, streamer, **model_kwargs)\u001b[0m\n\u001b[0;32m   3203\u001b[0m model_inputs\u001b[38;5;241m.\u001b[39mupdate({\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124moutput_hidden_states\u001b[39m\u001b[38;5;124m\"\u001b[39m: output_hidden_states} \u001b[38;5;28;01mif\u001b[39;00m output_hidden_states \u001b[38;5;28;01melse\u001b[39;00m {})\n\u001b[0;32m   3205\u001b[0m \u001b[38;5;66;03m# forward pass to get next token\u001b[39;00m\n\u001b[1;32m-> 3206\u001b[0m outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mmodel_inputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mreturn_dict\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m)\u001b[49m\n\u001b[0;32m   3208\u001b[0m \u001b[38;5;66;03m# synced_gpus: don't waste resources running the code we don't need; kwargs must be updated before skipping\u001b[39;00m\n\u001b[0;32m   3209\u001b[0m model_kwargs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_update_model_kwargs_for_generation(\n\u001b[0;32m   3210\u001b[0m     outputs,\n\u001b[0;32m   3211\u001b[0m     model_kwargs,\n\u001b[0;32m   3212\u001b[0m     is_encoder_decoder\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconfig\u001b[38;5;241m.\u001b[39mis_encoder_decoder,\n\u001b[0;32m   3213\u001b[0m )\n",
+      "File \u001b[1;32mf:\\TADBot\\.venv\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1736\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1734\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[0;32m   1735\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 1736\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\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[1;32mf:\\TADBot\\.venv\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1747\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1742\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[0;32m   1743\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[0;32m   1744\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_backward_pre_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\n\u001b[0;32m   1745\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m   1746\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[1;32m-> 1747\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[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\u001b[0;32m   1749\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m   1750\u001b[0m called_always_called_hooks \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mset\u001b[39m()\n",
+      "File \u001b[1;32mf:\\TADBot\\.venv\\Lib\\site-packages\\transformers\\models\\gemma2\\modeling_gemma2.py:1049\u001b[0m, in \u001b[0;36mGemma2ForCausalLM.forward\u001b[1;34m(self, input_ids, attention_mask, position_ids, past_key_values, inputs_embeds, labels, use_cache, output_attentions, output_hidden_states, return_dict, cache_position, num_logits_to_keep, **loss_kwargs)\u001b[0m\n\u001b[0;32m   1047\u001b[0m return_dict \u001b[38;5;241m=\u001b[39m return_dict \u001b[38;5;28;01mif\u001b[39;00m return_dict \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconfig\u001b[38;5;241m.\u001b[39muse_return_dict\n\u001b[0;32m   1048\u001b[0m \u001b[38;5;66;03m# decoder outputs consists of (dec_features, layer_state, dec_hidden, dec_attn)\u001b[39;00m\n\u001b[1;32m-> 1049\u001b[0m outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmodel\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m   1050\u001b[0m \u001b[43m    \u001b[49m\u001b[43minput_ids\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minput_ids\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1051\u001b[0m \u001b[43m    \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mattention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1052\u001b[0m \u001b[43m    \u001b[49m\u001b[43mposition_ids\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mposition_ids\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1053\u001b[0m \u001b[43m    \u001b[49m\u001b[43mpast_key_values\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mpast_key_values\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1054\u001b[0m \u001b[43m    \u001b[49m\u001b[43minputs_embeds\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minputs_embeds\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1055\u001b[0m \u001b[43m    \u001b[49m\u001b[43muse_cache\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muse_cache\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1056\u001b[0m \u001b[43m    \u001b[49m\u001b[43moutput_attentions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_attentions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1057\u001b[0m \u001b[43m    \u001b[49m\u001b[43moutput_hidden_states\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_hidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1058\u001b[0m \u001b[43m    \u001b[49m\u001b[43mreturn_dict\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mreturn_dict\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1059\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcache_position\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_position\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1060\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1062\u001b[0m hidden_states \u001b[38;5;241m=\u001b[39m outputs[\u001b[38;5;241m0\u001b[39m]\n\u001b[0;32m   1063\u001b[0m \u001b[38;5;66;03m# Only compute necessary logits, and do not upcast them to float if we are not computing the loss\u001b[39;00m\n",
+      "File \u001b[1;32mf:\\TADBot\\.venv\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1736\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1734\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[0;32m   1735\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 1736\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\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[1;32mf:\\TADBot\\.venv\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1747\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1742\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[0;32m   1743\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[0;32m   1744\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_backward_pre_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\n\u001b[0;32m   1745\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m   1746\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[1;32m-> 1747\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[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\u001b[0;32m   1749\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m   1750\u001b[0m called_always_called_hooks \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mset\u001b[39m()\n",
+      "File \u001b[1;32mf:\\TADBot\\.venv\\Lib\\site-packages\\transformers\\models\\gemma2\\modeling_gemma2.py:783\u001b[0m, in \u001b[0;36mGemma2Model.forward\u001b[1;34m(self, input_ids, attention_mask, position_ids, past_key_values, inputs_embeds, use_cache, output_attentions, output_hidden_states, return_dict, cache_position)\u001b[0m\n\u001b[0;32m    780\u001b[0m     use_cache \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m\n\u001b[0;32m    782\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m inputs_embeds \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m--> 783\u001b[0m     inputs_embeds \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43membed_tokens\u001b[49m\u001b[43m(\u001b[49m\u001b[43minput_ids\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    785\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m use_cache \u001b[38;5;129;01mand\u001b[39;00m past_key_values \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtraining:\n\u001b[0;32m    786\u001b[0m     batch_size, seq_len, _ \u001b[38;5;241m=\u001b[39m inputs_embeds\u001b[38;5;241m.\u001b[39mshape\n",
+      "File \u001b[1;32mf:\\TADBot\\.venv\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1736\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1734\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[0;32m   1735\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 1736\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\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[1;32mf:\\TADBot\\.venv\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1747\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1742\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[0;32m   1743\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[0;32m   1744\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_backward_pre_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\n\u001b[0;32m   1745\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m   1746\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[1;32m-> 1747\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[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\u001b[0;32m   1749\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m   1750\u001b[0m called_always_called_hooks \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mset\u001b[39m()\n",
+      "File \u001b[1;32mf:\\TADBot\\.venv\\Lib\\site-packages\\torch\\nn\\modules\\sparse.py:190\u001b[0m, in \u001b[0;36mEmbedding.forward\u001b[1;34m(self, input)\u001b[0m\n\u001b[0;32m    189\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[1;32m--> 190\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mF\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43membedding\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m    191\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[0;32m    192\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mweight\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    193\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpadding_idx\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    194\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmax_norm\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    195\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mnorm_type\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    196\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mscale_grad_by_freq\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    197\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msparse\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    198\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[1;32mf:\\TADBot\\.venv\\Lib\\site-packages\\torch\\nn\\functional.py:2551\u001b[0m, in \u001b[0;36membedding\u001b[1;34m(input, weight, padding_idx, max_norm, norm_type, scale_grad_by_freq, sparse)\u001b[0m\n\u001b[0;32m   2545\u001b[0m     \u001b[38;5;66;03m# Note [embedding_renorm set_grad_enabled]\u001b[39;00m\n\u001b[0;32m   2546\u001b[0m     \u001b[38;5;66;03m# XXX: equivalent to\u001b[39;00m\n\u001b[0;32m   2547\u001b[0m     \u001b[38;5;66;03m# with torch.no_grad():\u001b[39;00m\n\u001b[0;32m   2548\u001b[0m     \u001b[38;5;66;03m#   torch.embedding_renorm_\u001b[39;00m\n\u001b[0;32m   2549\u001b[0m     \u001b[38;5;66;03m# remove once script supports set_grad_enabled\u001b[39;00m\n\u001b[0;32m   2550\u001b[0m     _no_grad_embedding_renorm_(weight, \u001b[38;5;28minput\u001b[39m, max_norm, norm_type)\n\u001b[1;32m-> 2551\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mtorch\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43membedding\u001b[49m\u001b[43m(\u001b[49m\u001b[43mweight\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpadding_idx\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mscale_grad_by_freq\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43msparse\u001b[49m\u001b[43m)\u001b[49m\n",
+      "\u001b[1;31mRuntimeError\u001b[0m: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument index in method wrapper_CUDA__index_select)"
      ]
     }
    ],
    "source": [
     "%%time\n",
-    "input_text = \"I have so many issues to address. I have a history of sexual abuse, I’m a breast cancer survivor and I am a lifetime insomniac.    I have a long history of depression and I’m beginning to have anxiety. I have low self esteem but I’ve been happily married for almost 35 years.I’ve never had counseling about any of this. Do I have too many issues to address in counseling?\"\n",
-    "input_ids = tokenizer(input_text, return_tensors=\"pt\").to(\"cuda\")\n",
+    "input_ids = tokenizer(input_text, return_tensors=\"pt\")\n",
     "outputs = model.generate(**input_ids, max_length=2048)\n",
     "print(tokenizer.decode(outputs[0]))"
    ]
@@ -385,7 +236,12 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "model.save_pretrained(\"gemma2-TADBot\")\n",
+    "model.push_to_hub(\"gemma-2-2b-it-therapist\", use_auth_token=True, use_temp_dir=False)\n",
+    "tokenizer.save_pretrained(\"gemma-2-2b-it-therapist\")\n",
+    "tokenizer.push_to_hub(\"gemma-2-2b-it-therapist\", use_auth_token=True, use_temp_dir=False)"
+   ]
   }
  ],
  "metadata": {