Hugging Face's logo

nraptisss
/
telecom-intent-pipeline

Model card Files
xet
 Community
telecom-intent-pipeline
File size: 3,945 Bytes
a50bda6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Telecom Intent-to-Config Pipeline\n",
    "\n",
    "Fine-tune Qwen2.5-7B on your TMF921 intent dataset using QLoRA on Kaggle T4x2.\n",
    "\n",
    "## Step 1: Install Dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "source": [
    "!pip install -q transformers trl peft accelerate bitsandbytes datasets liger-kernel sentence-transformers huggingface-hub\n",
    "!pip install -q --upgrade transformers"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 2: Login to Hugging Face\n",
    "\n",
    "Get your token from https://huggingface.co/settings/tokens (needs `write` access)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "source": [
    "from huggingface_hub import notebook_login\n",
    "notebook_login()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 3: Download Scripts from Hub"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "source": [
    "!wget -q https://huggingface.co/nraptisss/telecom-intent-pipeline/resolve/main/train.py\n",
    "!wget -q https://huggingface.co/nraptisss/telecom-intent-pipeline/resolve/main/inference.py\n",
    "!wget -q https://huggingface.co/nraptisss/telecom-intent-pipeline/resolve/main/merge_and_push.py\n",
    "!wget -q https://huggingface.co/nraptisss/telecom-intent-pipeline/resolve/main/benchmark.py\n",
    "!ls -la"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 4: Run Training\n",
    "\n",
    "This takes ~2-3 hours on Kaggle T4x2 for 3 epochs on 30K samples.\n",
    "\n",
    "**Edit `train.py` first** if you want to change dataset, model, or hyperparameters."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "source": [
    "!python train.py"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 5: Test Inference"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "source": [
    "!python inference.py --intent \"Deploy a low-latency URLLC slice for autonomous drones in the harbor zone with 1ms latency and 99.999% reliability\""
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 6: Merge & Push to Hub"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "source": [
    "!python merge_and_push.py"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 7: Benchmark on Test Set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "source": [
    "!python benchmark.py --max_samples 100 --output benchmark_results.json"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## View Results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "source": [
    "import json\n",
    "with open('benchmark_results.json', 'r') as f:\n",
    "    data = json.load(f)\n",
    "\n",
    "print(f\"JSON Valid Rate: {data['summary']['json_valid_rate']:.1%}\")\n",
    "print(f\"Schema Compliance: {data['summary']['avg_schema_compliance']:.1%}\")\n",
    "if data['summary'].get('semantic_similarity_avg'):\n",
    "    print(f\"Semantic Similarity: {data['summary']['semantic_similarity_avg']:.3f}\")\n",
    "\n",
    "for layer, s in data['summary']['per_layer'].items():\n",
    "    print(f\"  {layer:20s} valid={s['valid_rate']:.1%} compliance={s['avg_compliance']:.1%}\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "name": "python",
   "version": "3.10.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}