Michael Marks commited on
Commit ·
dff620a
1
Parent(s): 3dd0806
add transformers notebook
Browse files- transformers.ipynb +71 -0
transformers.ipynb
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cells": [
|
| 3 |
+
{
|
| 4 |
+
"cell_type": "code",
|
| 5 |
+
"execution_count": 6,
|
| 6 |
+
"metadata": {},
|
| 7 |
+
"outputs": [
|
| 8 |
+
{
|
| 9 |
+
"name": "stdout",
|
| 10 |
+
"output_type": "stream",
|
| 11 |
+
"text": [
|
| 12 |
+
"Token was found\n",
|
| 13 |
+
"<|im_start|>system\n",
|
| 14 |
+
"You are an AI assistant with access to various tools.<|im_end|>\n",
|
| 15 |
+
"<|im_start|>user\n",
|
| 16 |
+
"Hi !<|im_end|>\n",
|
| 17 |
+
"<|im_start|>assistant\n",
|
| 18 |
+
"Hi human, what can help you with ?<|im_end|>\n",
|
| 19 |
+
"<|im_start|>assistant\n",
|
| 20 |
+
"\n"
|
| 21 |
+
]
|
| 22 |
+
}
|
| 23 |
+
],
|
| 24 |
+
"source": [
|
| 25 |
+
"import os\n",
|
| 26 |
+
"\n",
|
| 27 |
+
"from transformers import AutoTokenizer\n",
|
| 28 |
+
"\n",
|
| 29 |
+
"messages = [\n",
|
| 30 |
+
" {\"role\": \"system\", \"content\": \"You are an AI assistant with access to various tools.\"},\n",
|
| 31 |
+
" {\"role\": \"user\", \"content\": \"Hi !\"},\n",
|
| 32 |
+
" {\"role\": \"assistant\", \"content\": \"Hi human, what can help you with ?\"},\n",
|
| 33 |
+
"]\n",
|
| 34 |
+
"\n",
|
| 35 |
+
"token = os.getenv('HF_TOKEN')\n",
|
| 36 |
+
"if token is None:\n",
|
| 37 |
+
" raise ValueError('You must set the HF_TOKEN environment variable')\n",
|
| 38 |
+
"else:\n",
|
| 39 |
+
" print('Token was found')\n",
|
| 40 |
+
" #print('Token:', token)\n",
|
| 41 |
+
"\n",
|
| 42 |
+
"\n",
|
| 43 |
+
"tokenizer = AutoTokenizer.from_pretrained(\"HuggingFaceTB/SmolLM2-1.7B-Instruct\", use_auth_token=token)\n",
|
| 44 |
+
"rendered_prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)\n",
|
| 45 |
+
"\n",
|
| 46 |
+
"print(rendered_prompt)"
|
| 47 |
+
]
|
| 48 |
+
}
|
| 49 |
+
],
|
| 50 |
+
"metadata": {
|
| 51 |
+
"kernelspec": {
|
| 52 |
+
"display_name": "Python 3",
|
| 53 |
+
"language": "python",
|
| 54 |
+
"name": "python3"
|
| 55 |
+
},
|
| 56 |
+
"language_info": {
|
| 57 |
+
"codemirror_mode": {
|
| 58 |
+
"name": "ipython",
|
| 59 |
+
"version": 3
|
| 60 |
+
},
|
| 61 |
+
"file_extension": ".py",
|
| 62 |
+
"mimetype": "text/x-python",
|
| 63 |
+
"name": "python",
|
| 64 |
+
"nbconvert_exporter": "python",
|
| 65 |
+
"pygments_lexer": "ipython3",
|
| 66 |
+
"version": "3.13.2"
|
| 67 |
+
}
|
| 68 |
+
},
|
| 69 |
+
"nbformat": 4,
|
| 70 |
+
"nbformat_minor": 2
|
| 71 |
+
}
|