Downloads · 30 days
0
ad_lora-repo_dataset_v5_v2
SusumuDou/ad_lora-repo_dataset_v5_v2
ad_lora-repo_dataset_v5_v2 is a text generation model from SusumuDou. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
This repository provides a LoRA adapter fine-tuned from Qwen/Qwen3-4B-Instruct-2507 using LoRA + Unsloth.
Access
Public
Updated Feb 22, 2026
Parameters
4B
8.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8 GB · 100%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Feb 22, 2026
- Updated
- Feb 22, 2026
- SHA
- 3e23cdd9
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
qwen3-4b-agent-trajectory-lora
This repository provides a LoRA adapter fine-tuned from Qwen/Qwen3-4B-Instruct-2507 using LoRA + Unsloth.
This repository contains modified model.
Training Objective
This adapter is trained to improve multi-turn agent task performance on ALFWorld (household tasks) and DBBench (database operations).
Loss is applied to all assistant turns in the multi-turn trajectory, enabling the model to learn environment observation, action selection, tool use, and recovery from errors.
Training Configuration
- Base model: Qwen/Qwen3-4B-Instruct-2507
- Method: LoRA (full precision base)
- Max sequence length: 4096
- Epochs: 2
- Learning rate: 1e-05
- LoRA: r=64, alpha=128
Usage
base = "Qwen/Qwen3-4B-Instruct-2507"
Sources & Terms (IMPORTANT)
Training data: SusumuDou/alf_5_db_2
Dataset License: MIT License. This dataset is used and distributed under the terms of the MIT License. Compliance: Users must comply with the MIT license (including copyright notice) and the base model's original terms of use.
- Task
- Text Generation
- Library
- peft
- Type
- qwen3
- License
- apache-2.0
- Languages
- en
- Created
- Feb 22, 2026
- Updated
- Feb 22, 2026