{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from huggingface_hub import login\n",
    "from dotenv import load_dotenv\n",
    "import os\n",
    "load_dotenv()\n",
    "\n",
    "# Login to Hugging Face Hub\n",
    "login(token=os.getenv(\"HUGGINGFACE_TOKEN\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "3c50ceb1e4574215aeda5a9bef42a7b7",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/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, cache_dir=\".cache/\")\n",
    "tokenizer = AutoTokenizer.from_pretrained(model_name, cache_dir=\".cache/\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Gemma2ForCausalLM(\n",
      "  (model): Gemma2Model(\n",
      "    (embed_tokens): Embedding(256000, 2304, padding_idx=0)\n",
      "    (layers): ModuleList(\n",
      "      (0-25): 26 x Gemma2DecoderLayer(\n",
      "        (self_attn): Gemma2Attention(\n",
      "          (q_proj): Linear(in_features=2304, out_features=2048, bias=False)\n",
      "          (k_proj): Linear(in_features=2304, out_features=1024, bias=False)\n",
      "          (v_proj): Linear(in_features=2304, out_features=1024, bias=False)\n",
      "          (o_proj): Linear(in_features=2048, out_features=2304, bias=False)\n",
      "          (rotary_emb): Gemma2RotaryEmbedding()\n",
      "        )\n",
      "        (mlp): Gemma2MLP(\n",
      "          (gate_proj): Linear(in_features=2304, out_features=9216, bias=False)\n",
      "          (up_proj): Linear(in_features=2304, out_features=9216, bias=False)\n",
      "          (down_proj): Linear(in_features=9216, out_features=2304, bias=False)\n",
      "          (act_fn): PytorchGELUTanh()\n",
      "        )\n",
      "        (input_layernorm): Gemma2RMSNorm((2304,), eps=1e-06)\n",
      "        (pre_feedforward_layernorm): Gemma2RMSNorm((2304,), eps=1e-06)\n",
      "        (post_feedforward_layernorm): Gemma2RMSNorm((2304,), eps=1e-06)\n",
      "        (post_attention_layernorm): Gemma2RMSNorm((2304,), eps=1e-06)\n",
      "      )\n",
      "    )\n",
      "    (norm): Gemma2RMSNorm((2304,), eps=1e-06)\n",
      "  )\n",
      "  (lm_head): Linear(in_features=2304, out_features=256000, bias=False)\n",
      ")\n"
     ]
    }
   ],
   "source": [
    "print(model)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "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",
      "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: 31.2 s\n",
      "Wall time: 16.6 s\n"
     ]
    }
   ],
   "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",
    "\n",
    "input_ids = tokenizer(input_text, return_tensors=\"pt\")\n",
    "outputs = model.generate(**input_ids, max_length=128)\n",
    "print(tokenizer.decode(outputs[0]))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Model after fine tuning"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch\n",
    "from peft import PeftModel\n",
    "from transformers import AutoTokenizer, AutoModelForCausalLM\n",
    "\n",
    "# Load the base model and tokenizer\n",
    "model_name = \"google/gemma-2-2b-it\"\n",
    "# Load the fine-tuned model\n",
    "new_model = \"gemma-2-2b-ft/\"  # Replace with the path to your fine-tuned model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "be336a1628dd4c1ab7fe01f1179a44c0",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "base_model = AutoModelForCausalLM.from_pretrained(\n",
    "    model_name,\n",
    "    low_cpu_mem_usage=True,\n",
    "    return_dict=True,\n",
    "    torch_dtype=torch.float16,\n",
    "    cache_dir=\".cache/\"\n",
    ")\n",
    "model = PeftModel.from_pretrained(base_model, new_model, cache_dir = \".cache/\")\n",
    "model = model.merge_and_unload()\n",
    "\n",
    "# Reload tokenizer to save it\n",
    "tokenizer = AutoTokenizer.from_pretrained(\n",
    "    model_name, trust_remote_code=True, cache_dir=\".cache/\"\n",
    ")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mKeyboardInterrupt\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:1064\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   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\u001b[1;32m-> 1064\u001b[0m logits \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mlm_head\u001b[49m\u001b[43m(\u001b[49m\u001b[43mhidden_states\u001b[49m\u001b[43m[\u001b[49m\u001b[43m:\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m-\u001b[39;49m\u001b[43mnum_logits_to_keep\u001b[49m\u001b[43m:\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m:\u001b[49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1065\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconfig\u001b[38;5;241m.\u001b[39mfinal_logit_softcapping \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   1066\u001b[0m     logits \u001b[38;5;241m=\u001b[39m logits \u001b[38;5;241m/\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconfig\u001b[38;5;241m.\u001b[39mfinal_logit_softcapping\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\\linear.py:125\u001b[0m, in \u001b[0;36mLinear.forward\u001b[1;34m(self, input)\u001b[0m\n\u001b[0;32m    124\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--> 125\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mF\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mlinear\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\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\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mbias\u001b[49m\u001b[43m)\u001b[49m\n",
      "\u001b[1;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "%%time\n",
    "input_ids = tokenizer(input_text, return_tensors=\"pt\")\n",
    "outputs = model.generate(**input_ids, max_length=128)\n",
    "print(tokenizer.decode(outputs[0]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "f:\\TADBot\\.venv\\Lib\\site-packages\\transformers\\utils\\hub.py:894: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "2a177439e7c44497b5a90606031e3306",
       "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": "6258f1e1748746b7be0ce185383d1a2e",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Upload 2 LFS files:   0%|          | 0/2 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "aac825d586de4c308b2fdc32c3eb2709",
       "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"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "f:\\TADBot\\.venv\\Lib\\site-packages\\transformers\\utils\\hub.py:894: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "95379fa25d894a51bef847ec2b543487",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "README.md:   0%|          | 0.00/5.17k [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 C:\\Users\\Nitin Kausik Remella\\.cache\\huggingface\\hub\\models--ryefoxlime--Gemma-2-2B-it-Therapist. 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": "c8e5c1b9827643db8de5d51fb1df97e5",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "tokenizer.json:   0%|          | 0.00/34.4M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "CommitInfo(commit_url='https://huggingface.co/ryefoxlime/gemma-2-2b-it-therapist/commit/7ac88faf3ac432c4617e6e1b54969f12cc941e1e', commit_message='Upload tokenizer', commit_description='', oid='7ac88faf3ac432c4617e6e1b54969f12cc941e1e', pr_url=None, repo_url=RepoUrl('https://huggingface.co/ryefoxlime/gemma-2-2b-it-therapist', endpoint='https://huggingface.co', repo_type='model', repo_id='ryefoxlime/gemma-2-2b-it-therapist'), pr_revision=None, pr_num=None)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.save_pretrained(\"gemma-2-2b-it-therapist\")\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": {
  "kernelspec": {
   "display_name": ".venv",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}