Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more
Container

Run this model inference with full control and performance in your environment.

Learn more

Get help setting up a custom Dedicated Endpoints.

Talk with our engineer to get a quote for reserved GPU instances with discounts.

README

License: apache-2.0

Intended Use

The model is designed for e-commerce customer-service style responses, including:

  • product questions
  • logistics and shipping questions
  • return and refund questions
  • price protection questions
  • complaint handling and customer reassurance

Training Data

The training pipeline uses public customer-service/e-commerce datasets:

  • rescommons/Full-Ecom-Chatbot-Dataset
  • DianJin/DianJin-CSC-Data

Please review the original dataset licenses and terms before commercial use.

Training Method

  • Base model: Qwen/Qwen3-4B-Instruct-2507
  • Method: QLoRA
  • LoRA rank: 32 by default
  • Sequence length: 1024 by default
  • Hardware target: NVIDIA RTX 4070 Super 12GB

Limitations

This model is a personal portfolio fine-tune and should not be treated as a production customer-service system without additional evaluation, safety review, and business-policy grounding.

It may:

  • produce incorrect refund or warranty policy details
  • invent product information
  • fail on business-specific rules
  • respond inconsistently across Chinese and English

For production use, connect it to verified product, order, and policy data.

Example

text

User: 商品质量一般啊,我要退货
Assistant: 很抱歉让您有这样的体验。您可以先提供订单号和商品问题描述,我会帮您确认是否符合退货条件,并引导您提交退货申请。

Model provider

ronan7878

Model tree

Base

Qwen/Qwen3-4B-Instruct-2507

Fine-tuned

this model

Modalities

Input

Text

Output

Text

Pricing

Dedicated Endpoints

View details

Supported Functionality

Model APIs

Dedicated Endpoints

Container

More information

Explore FriendliAI today