agentbenchfinal / README.md
takayosh's picture
Upload final merged Qwen2.5-7B-Instruct ALF+DBB model
5727d2d verified
metadata
base_model: Qwen/Qwen2.5-7B-Instruct
datasets:
  - u-10bei/sft_alfworld_trajectory_dataset_v5
  - u-10bei/dbbench_sft_dataset_react_v4
language:
  - en
license: apache-2.0
library_name: peft
pipeline_tag: text-generation
tags:
  - lora
  - agent
  - tool-use
  - alfworld
  - dbbench

qwen2.5-7b-alf-dbb-merged-final

This repository provides a merged full model based on Qwen/Qwen2.5-7B-Instruct.

Model Construction Pipeline

  1. Train LoRA adapter on ALFWorld
  2. Train LoRA adapter on DBBench
  3. Merge adapters using ties (density=0.1)
  4. Apply additional stabilization fine-tuning (LoRA)
  5. Merge final adapter into base model

This repository contains full merged weights (no adapter required).

Final Training Configuration

  • Base model: Qwen/Qwen2.5-7B-Instruct
  • Merge method: ties
  • Merge density: 0.1
  • Final stage epochs: 1
  • Learning rate: 1e-05
  • Final LoRA: r=16, alpha=16
  • Max sequence length: 2024

Datasets

  • u-10bei/sft_alfworld_trajectory_dataset_v5
  • u-10bei/dbbench_sft_dataset_react_v4

Additional distilled datasets were optionally included.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "takayosh/agentbenchfinal"

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

Sources & Terms (IMPORTANT)

Training data:

  • u-10bei/sft_alfworld_trajectory_dataset_v5
  • 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.