Upload working.ipynb

working.ipynb

@@ -0,0 +1,333 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "60299a7f-6e86-4bd6-9dbf-250b42a264b9",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "🦥 Unsloth: Will patch your computer to enable 2x faster free finetuning.\n",
+      "==((====))==  Unsloth 2024.8: Fast Llama patching. Transformers = 4.44.2.\n",
+      "   \\\\   /|    GPU: NVIDIA GeForce RTX 3090. Max memory: 23.691 GB. Platform = Linux.\n",
+      "O^O/ \\_/ \\    Pytorch: 2.3.0. CUDA = 8.6. CUDA Toolkit = 12.1.\n",
+      "\\        /    Bfloat16 = TRUE. FA [Xformers = 0.0.27. FA2 = False]\n",
+      " \"-____-\"     Free Apache license: http://github.com/unslothai/unsloth\n"
+     ]
+    }
+   ],
+   "source": [
+    "from unsloth import FastLanguageModel\n",
+    "import torch\n",
+    "max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!\n",
+    "dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+\n",
+    "load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.\n",
+    "\n",
+    "model, tokenizer = FastLanguageModel.from_pretrained(\n",
+    "    model_name = \"unsloth/Phi-3.5-mini-instruct\",\n",
+    "    max_seq_length = max_seq_length,\n",
+    "    dtype = dtype,\n",
+    "    load_in_4bit = load_in_4bit,\n",
+    "    # token = \"hf_...\", # use one if using gated models like meta-llama/Llama-2-7b-hf\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "8712c5c8-c763-4743-bc8d-54b879433b73",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Unsloth 2024.8 patched 32 layers with 32 QKV layers, 32 O layers and 32 MLP layers.\n"
+     ]
+    }
+   ],
+   "source": [
+    "model = FastLanguageModel.get_peft_model(\n",
+    "    model,\n",
+    "    r = 16, # Choose any number > 0 ! Suggested 8, 16, 32, 64, 128\n",
+    "    target_modules = [\"q_proj\", \"k_proj\", \"v_proj\", \"o_proj\",\n",
+    "                      \"gate_proj\", \"up_proj\", \"down_proj\",],\n",
+    "    lora_alpha = 16,\n",
+    "    lora_dropout = 0, # Supports any, but = 0 is optimized\n",
+    "    bias = \"none\",    # Supports any, but = \"none\" is optimized\n",
+    "    # [NEW] \"unsloth\" uses 30% less VRAM, fits 2x larger batch sizes!\n",
+    "    use_gradient_checkpointing = \"unsloth\", # True or \"unsloth\" for very long context\n",
+    "    random_state = 3407,\n",
+    "    use_rslora = False,  # We support rank stabilized LoRA\n",
+    "    loftq_config = None, # And LoftQ\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "c9d36fef-4c62-412d-81a8-2769a1b56042",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "3df9b30fca4c43f59d13de16a849d74b",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading data:   0%|          | 0.00/14.5k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "a8721bd6c057407caa6b34f73ffde6af",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Generating train split:   0%|          | 0/10 [00:00<?, ? examples/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from datasets import load_dataset\n",
+    "dataset = load_dataset(\"arbinMichael/testparquet\", split = \"train\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "452ad49e-b283-4655-9c99-f30c5eed681c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<|user|>Perpare a schedule for current charge/discharge test, the value of the current is a linear variable, using Current Ramp(A) control type. The charging current start value is 0.5A, the rate of change of the current per second is 0.01, up to 4V then ; discharge current start value is -0.5A, the rate of change of the current per second is -0.01, discharging to 1V then end the test. Record one point per second<|end|><|assistant|>[{\"StepCtrlTypeString\":\"Rest\",\"CtrlValue\":\"\",\"Label\":\"Step_A\",\"StepLimits\":[{\"Equations\":\"PV_CHAN_Step_Time>=5\",\"GotoStep\":\"Next Step\"}],\"LogLimits\":[{\"Equations\":\"DV_Time>=1\",\"GotoStep\":\"Next Step\"}]},{\"StepCtrlTypeString\":\"Current Ramp(A)\",\"CtrlValue\":\"0.5\",\"Label\":\"Step_B\",\"StepLimits\":[{\"Equations\":\"PV_CHAN_Voltage>=4\",\"GotoStep\":\"Next Step\"}],\"LogLimits\":[{\"Equations\":\"DV_Time>=1\",\"GotoStep\":\"Next Step\"}]},{\"StepCtrlTypeString\":\"Current Ramp(A)\",\"CtrlValue\":\"-0.5\",\"Label\":\"Step_C\",\"StepLimits\":[{\"Equations\":\"PV_CHAN_Voltage<=1\",\"GotoStep\":\"Next Step\"}],\"LogLimits\":[{\"Equations\":\"DV_Time>=1\",\"GotoStep\":\"Next Step\"}]}]<|end|>\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(dataset[5][\"text\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "b0a39d9e-e3bf-4fae-8d75-dba12ccf15c8",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "da8408ab10ec44358873ee0f1c234abd",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Map (num_proc=2):   0%|          | 0/10 [00:00<?, ? examples/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "max_steps is given, it will override any value given in num_train_epochs\n"
+     ]
+    }
+   ],
+   "source": [
+    "from trl import SFTTrainer\n",
+    "from transformers import TrainingArguments\n",
+    "from unsloth import is_bfloat16_supported\n",
+    "\n",
+    "trainer = SFTTrainer(\n",
+    "    model = model,\n",
+    "    tokenizer = tokenizer,\n",
+    "    train_dataset = dataset,\n",
+    "    dataset_text_field = \"text\",\n",
+    "    max_seq_length = max_seq_length,\n",
+    "    dataset_num_proc = 2,\n",
+    "    packing = False, # Can make training 5x faster for short sequences.\n",
+    "    args = TrainingArguments(\n",
+    "        per_device_train_batch_size = 2,\n",
+    "        gradient_accumulation_steps = 4,\n",
+    "        warmup_steps = 5,\n",
+    "        max_steps = 60,\n",
+    "        learning_rate = 2e-4,\n",
+    "        fp16 = not is_bfloat16_supported(),\n",
+    "        bf16 = is_bfloat16_supported(),\n",
+    "        logging_steps = 1,\n",
+    "        optim = \"adamw_8bit\",\n",
+    "        weight_decay = 0.01,\n",
+    "        lr_scheduler_type = \"linear\",\n",
+    "        seed = 7444,\n",
+    "        output_dir = \"outputs\",\n",
+    "    ),\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "625e8b31-82d8-4930-a46e-a82803b4f211",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "==((====))==  Unsloth - 2x faster free finetuning | Num GPUs = 1\n",
+      "   \\\\   /|    Num examples = 10 | Num Epochs = 60\n",
+      "O^O/ \\_/ \\    Batch size per device = 2 | Gradient Accumulation steps = 4\n",
+      "\\        /    Total batch size = 8 | Total steps = 60\n",
+      " \"-____-\"     Number of trainable parameters = 29,884,416\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "    <div>\n",
+       "      \n",
+       "      <progress value='9' max='60' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
+       "      [ 9/60 03:36 < 26:20, 0.03 it/s, Epoch 6.40/60]\n",
+       "    </div>\n",
+       "    <table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       " <tr style=\"text-align: left;\">\n",
+       "      <th>Step</th>\n",
+       "      <th>Training Loss</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <td>1</td>\n",
+       "      <td>1.464500</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2</td>\n",
+       "      <td>1.716400</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>3</td>\n",
+       "      <td>1.345900</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>4</td>\n",
+       "      <td>1.429800</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>5</td>\n",
+       "      <td>1.709500</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>6</td>\n",
+       "      <td>1.453600</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>7</td>\n",
+       "      <td>1.219900</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table><p>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "trainer_stats = trainer.train()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 57,
+   "id": "c407b9c0-aa4c-412a-b7cc-ddbdbb6a5212",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "19796902751<|end|><|assistant|> This number is a unique identifier, often used for telephone numbers or other personalized services.<|end|><|endoftext|>\n"
+     ]
+    }
+   ],
+   "source": [
+    "from unsloth.chat_templates import get_chat_template\n",
+    "\n",
+    "tokenizer = get_chat_template(\n",
+    "    tokenizer,\n",
+    "    chat_template = \"phi-3\", # Supports zephyr, chatml, mistral, llama, alpaca, vicuna, vicuna_old, unsloth\n",
+    "    mapping = {\"role\" : \"from\", \"content\" : \"value\", \"user\" : \"human\", \"assistant\" : \"gpt\"}, # ShareGPT style\n",
+    ")\n",
+    "\n",
+    "FastLanguageModel.for_inference(model) # Enable native 2x faster inference\n",
+    "\n",
+    "messages = [\n",
+    "    {\"from\": \"human\", \"value\": \"19796902751 who uses this number?\"},\n",
+    "]\n",
+    "inputs = tokenizer.apply_chat_template(\n",
+    "    messages,\n",
+    "    tokenize = True,\n",
+    "    add_generation_prompt = True, # Must add for generation\n",
+    "    return_tensors = \"pt\",\n",
+    ").to(\"cuda\")\n",
+    "\n",
+    "from transformers import TextStreamer\n",
+    "text_streamer = TextStreamer(tokenizer, skip_prompt = True)\n",
+    "_ = model.generate(input_ids = inputs, streamer = text_streamer, max_new_tokens = 128, use_cache = True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "069d4087-35c2-4d2e-b981-f5bc65bac44d",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.11.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}