qwen2.5-7b-agent-trajectory-lora-v3_35_47C2
This repository provides a LoRA adapter fine-tuned from
unsloth/Qwen2.5-7B-Instruct using LoRA + Unsloth.
This repository contains LoRA adapter weights only.
The base model must be loaded separately.
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/Qwen2.5-7B-Instruct
- Method: LoRA (full precision base)
- Max sequence length: 2048
- Epochs: 3
- Learning rate: 3e-05
- LoRA: r=32, alpha=32
Usage
Since this is a merged model, you can use it directly with transformers.
1from transformers import AutoModelForCausalLM, AutoTokenizer
2import torch
3
4model_id = "your_id/your-repo-name"
5
6tokenizer = AutoTokenizer.from_pretrained(model_id)
7model = AutoModelForCausalLM.from_pretrained(
8 model_id,
9 torch_dtype=torch.float16,
10 device_map="auto",
11)
12
Sources & Terms (IMPORTANT)
Training data: 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;u-10bei/sft_alfworld_trajectory_dataset;u-10bei/sft_alfworld_trajectory_dataset_v2;openai/gsm8k
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.
