File size: 4,077 Bytes
3a2b5d2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "1128b0b6-b3a1-4553-a284-b1206b3c5a09",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "INFO:nncf:NNCF initialized successfully. Supported frameworks detected: torch, onnx, openvino\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/anish/miniconda3/envs/pytorch_test/lib/python3.11/site-packages/transformers/utils/import_utils.py:519: FutureWarning: `is_torch_tpu_available` is deprecated and will be removed in 4.41.0. Please use the `is_torch_xla_available` instead.\n",
      "  warnings.warn(\n",
      "/home/anish/miniconda3/envs/pytorch_test/lib/python3.11/site-packages/diffusers/utils/outputs.py:63: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.\n",
      "  torch.utils._pytree._register_pytree_node(\n"
     ]
    }
   ],
   "source": [
    "from optimum.intel import OVModelForCausalLM\n",
    "from transformers import AutoConfig, AutoTokenizer, BitsAndBytesConfig\n",
    "import torch\n",
    "import os"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "d0f822f2-2bac-4b7e-bf6c-1117a836eb46",
   "metadata": {},
   "outputs": [],
   "source": [
    "tokenizer = AutoTokenizer.from_pretrained(\"/home/anish/dockerx/Buildarea/LLMs/Mistral-7B-Instruct-v0.2/int4-sym-g64\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "05cf6ff2-2aba-438d-ac78-73bfc9a50139",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Compiling the model to CPU ...\n"
     ]
    }
   ],
   "source": [
    "model = OVModelForCausalLM.from_pretrained(\"/home/anish/dockerx/Buildarea/LLMs/Mistral-7B-Instruct-v0.2/int4-sym-g64\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "c3769b36-2a6e-48f9-9cb7-2a3df894bee3",
   "metadata": {},
   "outputs": [],
   "source": [
    "prompt = \"do you want phull sapport saar?\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "05e51bb7-5610-447b-b5e9-6882b1515ed3",
   "metadata": {},
   "outputs": [],
   "source": [
    "text = \"[INST]Write me hello world in python language[\\INST]\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "d50de6df-d452-4f7d-9bfb-25bb4a4137ad",
   "metadata": {},
   "outputs": [],
   "source": [
    "model_inputs = tokenizer([prompt], return_tensors=\"pt\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "59651efc-f6d1-48ff-900c-fff926f36728",
   "metadata": {},
   "outputs": [],
   "source": [
    "generated_ids = model.generate(**model_inputs, max_length=1024, pad_token_id=2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "0e1e29bb-0fe0-420f-9e7a-3dd8996676dc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'<s> do you want phull sapport saar?\\n\\nI\\'m not entirely sure I understand your question. Could you please clarify what you mean by \"phull sapport saar\" and what type of support you\\'re asking for? I\\'ll do my best to help you out.</s>'"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tokenizer.batch_decode(generated_ids)[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d6d2616b-ac6e-4996-95ab-4661a84bc75d",
   "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": "3.11.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}