Upload llllmmm.ipynb

llllmmm.ipynb

@@ -0,0 +1,144 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "id": "initial_id",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-07-01T11:08:00.253851Z",
+     "start_time": "2024-07-01T11:08:00.067738Z"
+    }
+   },
+   "source": [
+    "import torch\n",
+    "from transformers import AutoTokenizer, AutoModelForCausalLM,TrainingArguments\n",
+    "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")"
+   ],
+   "outputs": [],
+   "execution_count": 2
+  },
+  {
+   "cell_type": "code",
+   "id": "df5ce2489db64f8d",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-07-01T11:08:15.731889Z",
+     "start_time": "2024-07-01T11:08:03.640950Z"
+    }
+   },
+   "source": [
+    "model = AutoModelForCausalLM.from_pretrained(\"meta-llama/Llama-2-7b-hf\", device_map=\"auto\", torch_dtype = \"auto\",cache_dir=\"D:/a\" )\n",
+    "tokenizer = AutoTokenizer.from_pretrained(\"meta-llama/Llama-2-7b-hf\", cache_dir=\"D:/a\", use_fast=True)"
+   ],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]"
+      ],
+      "application/vnd.jupyter.widget-view+json": {
+       "version_major": 2,
+       "version_minor": 0,
+       "model_id": "475b288bdaa84157adbb7b99f89c7e5c"
+      }
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "WARNING:root:Some parameters are on the meta device device because they were offloaded to the disk.\n"
+     ]
+    }
+   ],
+   "execution_count": 3
+  },
+  {
+   "cell_type": "code",
+   "id": "7ce8ee88e61ac738",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-07-01T11:08:50.346303Z",
+     "start_time": "2024-07-01T11:08:50.336252Z"
+    }
+   },
+   "source": [
+    "def get_llama2_response(prompt, max_new_tokens=50):\n",
+    "     inputs = tokenizer(prompt, return_tensors=\"pt\").to(device)\n",
+    "     outputs = model.generate(**inputs, max_new_tokens=max_new_tokens, temperature= 0.00001)\n",
+    "     response = tokenizer.decode(outputs(0), skip_special_tokens=True)\n",
+    "     return response"
+   ],
+   "outputs": [],
+   "execution_count": 7
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Q:how to find the llama A:The llama is a South American camelid, a domesticated species of the genus Lama. It is used for'"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "execution_count": 9,
+   "source": [
+    "prompt = \"Q:how to find the llama A:\"\n",
+    "get_llama2_response(prompt, max_new_tokens=25)"
+   ],
+   "id": "a6ad65ea85069793"
+  },
+  {
+   "metadata": {
+    "jupyter": {
+     "is_executing": true
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "prompt = \"Q:SQL query to extract data from Employee Table A:\"\n",
+    "get_llama2_response(prompt, max_new_tokens=25)"
+   ],
+   "id": "de9f0fcc6dc9fa82",
+   "outputs": [],
+   "execution_count": null
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "source": "",
+   "id": "e7f9c4411f2d8b57",
+   "outputs": [],
+   "execution_count": null
+  }
+ ],
+ "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": "3.12.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}