You can deploy this model and start earning money today!

satoyutaka/
Qwen3-4B-AgentBench-llm2025_advance_1st

Name: Qwen3-4B-AgentBench-llm2025_advance_1st
Availability: InStock

safetensors

qwen3

Views

No views yet

Qwen3-4B-AgentBench-llm2025_advance_1st

This is the initial V1 version of the specialized Agent model for AgentBench-comp, based on the Qwen3-4B-Instruct-2507 architecture.

🚀 Overview

Base Architecture: Qwen3-4B-Instruct-2507
Task Focus: Optimized for DB Bench (SQL) and ALFWorld (Action Planning).
Compliance: 100% synthetic data generated by teacher models. No original competition data used.

Usage (Standard Transformers)

python

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "satoyutaka/Qwen3-4B-AgentBench-llm2025_advance_1st"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto"
)

[日本語訳] Qwen3-4B-AgentBench-llm2025_advance_1st

本モデルは、AgentBench-comp向けに開発された、Qwen3-4B-Instruct-2507ベースの初期エージェントモデル（V1）です。

🚀 概要

ベースアーキテクチャ: Qwen3-4B-Instruct-2507
重点タスク: DB Bench (SQL) および ALFWorld (行動計画) に最適化。
ポリシー: 全データ合成データを使用。競技規約を完全に遵守しています。