TINGJUNN
/

qwen3-backward-model

Model card Files Files and versions

Backward Model

LoRA fine-tuned Qwen3-1.7B for generating instructions from responses.

Training: OpenAssistant-Guanaco (2000 samples)
Method: LoRA (r=16, α=32)
Assignment: DSAA 6000Q Assignment 3

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for TINGJUNN/qwen3-backward-model

Base model

Qwen/Qwen3-1.7B-Base

Finetuned

Qwen/Qwen3-1.7B

Adapter

(779)

this model