Downloads · 30 days
0
telecom-troubleshooter-qwen2.5-3b-lora
Rislantrs/telecom-troubleshooter-qwen2.5-3b-lora
telecom-troubleshooter-qwen2.5-3b-lora is a text generation model from Rislantrs. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
Model ini adalah hasil Fine-Tuning QLoRA 4-bit dari unsloth/Qwen2.5-3B-Instruct pada Dataset SFT Telekomunikasi Indonesia (TelkomNusa).
Access
Public
Updated Aug 26, 2026
Repo size
251 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors120 MB · 91%
At a glance
- Task
- Text Generation
- License
- apache-2.0
- Access
- Public
- Created
- Jul 20, 2026
- Updated
- Aug 26, 2026
- SHA
- c7e28a08
Base models
Model card
From the Hugging Face model README
🇮🇩 Qwen2.5-3B-Instruct - TelkomNusa BSS Indonesian AI Agent (QLoRA Adapter)
Model ini adalah hasil Fine-Tuning QLoRA 4-bit dari unsloth/Qwen2.5-3B-Instruct pada Dataset SFT Telekomunikasi Indonesia (TelkomNusa).
🎯 Kemampuan Model:
- 23 Tool API BSS TelkomNusa: Ekstraksi parameter akurat untuk Billing, Kuota Data, Paket Roaming, Kupon Extra, Layanan Keluarga, dan Add-on.
- Format Native ChatML Tool-Calling: Menggunakan tag
<tool_call>{"name": ..., "arguments": ...}</tool_call>standar Qwen2.5. - Bahasa Indonesia Alami: Luwes merespons pertanyaan pelanggan dalam bahasa Indonesia lokal.
📊 Konfigurasi Pelatihan:
- Arsitektur PEFT: LoRA Rank 16, Alpha 32, Target: All Linear Layers (
q,k,v,o,gate,up,down_proj). - Framework: Unsloth Fast AI + TRL SFTTrainer.
- Task
- Text Generation
- License
- apache-2.0
- Languages
- id
- Created
- Jul 20, 2026
- Updated
- Aug 26, 2026