metadata
base_model: unsloth/Qwen3-4B-Instruct-2507
datasets:
- u-10bei/sft_alfworld_trajectory_dataset_v2
- u-10bei/sft_alfworld_trajectory_dataset_v3
- u-10bei/sft_alfworld_trajectory_dataset_v4
- u-10bei/sft_alfworld_trajectory_dataset_v5
- u-10bei/dbbench_sft_dataset_react
- u-10bei/dbbench_sft_dataset_react_v2
- u-10bei/dbbench_sft_dataset_react_v3
- u-10bei/dbbench_sft_dataset_react_v4
language:
- en
license: apache-2.0
library_name: transformers
pipeline_tag: text-generation
tags:
- lora
- agent
- tool-use
- alfworld
- dbbench
＜qwen3-4b-agent-trajectory-lora＞
This repository provides a merged model that includes both the base model unsloth/Qwen3-4B-Instruct-2507 and the LoRA adapter. No separate LoRA loading is required.
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: unsloth/Qwen3-4B-Instruct-2507
- Method: LoRA
- dtype: torch.bfloat16
- load_in_4bit: False
- Max sequence length: 1024
- Epochs: 1
- Learning rate: 2e-06
- LoRA: r=64, alpha=128
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_id = "da1ch812/advanced-comp-model"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.float16,
device_map="auto",
)
Sources & Terms (IMPORTANT)
Training data:
- u-10bei/sft_alfworld_trajectory_dataset_v2
- u-10bei/sft_alfworld_trajectory_dataset_v3
- u-10bei/sft_alfworld_trajectory_dataset_v4
- u-10bei/sft_alfworld_trajectory_dataset_v5
- u-10bei/dbbench_sft_dataset_react
- u-10bei/dbbench_sft_dataset_react_v2
- u-10bei/dbbench_sft_dataset_react_v3
- u-10bei/dbbench_sft_dataset_react_v4
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.