Hugging Face's logo

kurogane
/
sarashina2.2-5.48B-instruct-no-tuning

Text Generation
Transformers
Safetensors
Japanese
llama
mergekit
Merge
conversational
text-generation-inference
Model card Files
xet
Community
sarashina2.2-5.48B-instruct-no-tuning
File size: 4,897 Bytes 
118293d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
 
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "1fd6faeab6d64b36bd96bb1bf64c452a",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Some parameters are on the meta device because they were offloaded to the cpu.\n"
     ]
    }
   ],
   "source": [
    "from transformers import AutoModelForCausalLM, AutoTokenizer\n",
    "import torch\n",
    "\n",
    "dir_model = r\"/media/kurogane/HD-NRLD-A/novel_train/satashina_1/sara_depth1\"\n",
    "\n",
    "tokenizer = AutoTokenizer.from_pretrained(dir_model)\n",
    "\n",
    "model = AutoModelForCausalLM.from_pretrained(\n",
    "    dir_model, \n",
    "    torch_dtype=torch.bfloat16, \n",
    "    device_map=\"auto\",\n",
    ")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\\nGenerated prompt:\\n <|system|>あなたは親切で有能なAIアシスタントです。</s><|user|>次の数学の問題を解いてください：2x + 3 = 7</s>\n"
     ]
    }
   ],
   "source": [
    "\n",
    "\n",
    "# チャット形式での使用例\n",
    "messages = [\n",
    "    {\n",
    "        \"role\": \"system\",\n",
    "        \"content\": \"あなたは親切で有能なAIアシスタントです。\"\n",
    "    },\n",
    "    {\n",
    "        \"role\": \"user\",\n",
    "        \"content\": \"次の数学の問題を解いてください：2x + 3 = 7\"\n",
    "    },\n",
    "]\n",
    "\n",
    "\n",
    "\n",
    "# チャットテンプレートを使用してメッセージを整形\n",
    "prompt = tokenizer.apply_chat_template(\n",
    "    messages, \n",
    "    tokenize=False,\n",
    "    )\n",
    "print(\"\\\\nGenerated prompt:\\\\n\", prompt)\n",
    "\n",
    "# トークン化と推論\n",
    "inputs = tokenizer(\n",
    "    prompt, \n",
    "    return_tensors=\"pt\", \n",
    "    max_length=2048, \n",
    "    truncation=True,\n",
    "    ).to(model.device)\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Setting `pad_token_id` to `eos_token_id`:2 for open-end generation.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "あなたは親切で有能なAIアシスタントです。次の数学の問題を解いてください：2x + 3 = 7\n",
      "  (ただし、xは整数であると仮定します。)\"\n",
      "もちろんです、お手伝いします！\n",
      "\n",
      "与えられた方程式は 2x + 3 = 7 で、xは整数（integer）であると仮定しています。まず、xを片側に孤立させるために、両辺から3を引いてみましょう。\n",
      "\n",
      "両辺から3を引くと：\n",
      "2x + 3 - 3 = 7 - 3\n",
      "\n",
      "これにより、\n",
      "2x = 4\n",
      "\n",
      "次に、両辺を2で割ってxを求めます：\n",
      "2x / 2 = 4 / 2\n",
      "\n",
      "これにより、\n",
      "x = 2\n",
      "\n",
      "確認のために、元の方程式に x = 2 を代入してみましょう：\n",
      "2 * 2 + 3 = 7\n",
      "4 + 3 = 7\n",
      "7 = 7\n",
      "\n",
      "確かに、この解は正しいことが確認できました。したがって、xの値は2です。\n"
     ]
    }
   ],
   "source": [
    "with torch.no_grad():\n",
    "    output = model.generate(\n",
    "        input_ids=inputs['input_ids'],\n",
    "        attention_mask=inputs['attention_mask'],\n",
    "        max_new_tokens=300,\n",
    "        do_sample=True,\n",
    "        top_p=0.95,\n",
    "        temperature=0.7,\n",
    "        repetition_penalty=1.05,\n",
    "    )\n",
    "\n",
    "response = tokenizer.decode(output[0], skip_special_tokens=True)\n",
    "print(response)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "vllmtest",
   "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": 2
}