mssfj/Qwen2.5-7B-Instruct_alfworld_dbbench_grpo_merge-2

Qwen2.5-7B-Instruct ALFWorld + DBBench GRPO Merge

This repository provides a merged model derived from GRPO-trained checkpoints based on mssfj/Qwen2.5-7B-Instruct_grpo_alfworld_trajectory_dataset and mssfj/Qwen2.5-7B-Instruct_dbbench_grpo_dataset_react.

The source GRPO models were trained with LoRA + Unsloth/TRL GRPO and then merged. This repository contains full merged model weights (not adapter-only weights).

Training Objective

This model 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/Qwen2.5-7B-Instruct
• Intermediate model (ALFWorld GRPO run): mssfj/Qwen2.5-7B-Instruct_grpo_alfworld_trajectory_dataset
• Intermediate model (DBBench GRPO run): mssfj/Qwen2.5-7B-Instruct_dbbench_grpo_dataset_react
• Merge base model: mssfj/Qwen2.5-7B-Instruct_grpo_alfworld_trajectory_dataset
• Merge method: linear
• Merge weights: 0.75 (ALFWorld GRPO) + 0.25 (DBBench GRPO)
• Merge dtype: bfloat16
• Method: LoRA (full precision base) + GRPO, then merge
• Max sequence length: 2048
• Epochs: N/A (step-based GRPO training)
• Learning rate: 5e-5
• LoRA: r=16, alpha=32
• GRPO steps: 200 (ALFWorld), 125 (DBBench)
• GRPO batch config: per_device_train_batch_size=4, gradient_accumulation_steps=2, num_generations=8

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "mssfj/Qwen2.5-7B-Instruct_alfworld_dbbench_grpo_merge-2"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

Sources & Terms (IMPORTANT)

Training data:

• u-10bei/sft_alfworld_trajectory_dataset
• u-10bei/dbbench_sft_dataset_react

Dataset License: MIT License. These datasets are 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.