You can deploy this model and start earning money today!

NobutaMN/
qwen25-7b-sft1-mix2-batch3-base-maxsteps-1_epo1_1.75e-6

Name: qwen25-7b-sft1-mix2-batch3-base-maxsteps-1_epo1_1.75e-6
Availability: InStock

Qwen/Qwen2.5-7B-Instruct

adapter

apache-2.0

Views

No views yet

qwen25-7b-sft1-mix2_batch3-base-epo1_-1-1.75e-6_db1261alf2317

This repository provides a LoRA adapter fine-tuned from Qwen/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: Qwen/Qwen2.5-7B-Instruct
Method: LoRA (full precision base)
Max sequence length: 2048
Epochs: 1
Learning rate: 2e-06
LoRA: r=64, alpha=128

Usage

python

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

base = "Qwen/Qwen2.5-7B-Instruct"
adapter = "your_id/your-repo"

tokenizer = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(
    base,
    torch_dtype=torch.float16,
    device_map="auto",
)
model = PeftModel.from_pretrained(model, adapter)

Sources & Terms (IMPORTANT)

Training data: ★★★mix2_batch3_db1261alf2317.jsonl (local, ALF 1261 + DB 2317)

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.

NobutaMN/qwen25-7b-sft1-mix2-batch3-base-maxsteps-1_epo1_1.75e-6