You can deploy this model and start earning money today!

qwen2.5-7b-instruct-sft-v5

Name: qwen2.5-7b-instruct-sft-v5
Availability: InStock

This repository provides a merged full model produced by supervised fine-tuning for AgentBench-oriented ALFWorld/DBBench robustness.

Training Objective

Improve strict action selection reliability for ALFWorld prompts and strengthen SQL error-recovery robustness for DBBench prompts, while keeping balanced mixed-task behavior.

Training Configuration

Method: SFT (Unsloth LoRA) + merge to full model
Base model ID (upstream): Qwen/Qwen2.5-7B-Instruct
Initialization model for this stage: prior merged checkpoint from the previous advanced retraining stage
LoRA: r=16, alpha=32, dropout=0.0
LoRA target modules: q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj
Output learn mode: from_marker (ACTION: and Action: markers)
Max sequence length: 4096
Max steps: 400
Epochs: 1
Learning rate: 2.0e-6
Per-device train batch size: 1
Per-device eval batch size: 2
Gradient accumulation steps: 32
Effective global batch size: 32
Warmup ratio: 0.03
Weight decay: 0.01
Eval/Save steps: 50 / 25

Usage

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "uchkw/qwen2.5-7b-instruct-sft-v5"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

Training Data / Sources & License (IMPORTANT)

Primary source datasets:
- u-10bei/sft_alfworld_trajectory_dataset_v5
- u-10bei/dbbench_sft_dataset_react_v4
- u-10bei/dbbench_sft_dataset_react_v3
Data construction policy (concise):
- ALFWorld samples were converted into strict one-line action supervision (ACTION: ...) with exact matching against AVAILABLE ACTIONS.
- Added hard-copy style ALF augmentation to reinforce exact action copying and reduce formatting drift.
- Mixed DBBench supervision and recovery-oriented examples for Unknown column style failures.
- Mixed train ratio was controlled at approximately ALF:DB = 55:45.
Dataset scale (fix8 stage2):
- Train samples: 138496
- Validation samples: 7289
- Train ALF rows: 76173
- Train DB rows: 62323
- ALF strict-match in training set: 1.0
- ALF completion-verb ratio: 0.4726
- ALF toggle rows: 1772
Evaluation snapshot (checkpoint-50, official_v02 setting):
- DB overall_cat_accuracy: 0.5180407064
- ALF success_rate: 0.62
- ALF invalid_action_rate: 0.14
- ALF task_limit_rate: 0.24
Compliance:
- Follow each source dataset card and license terms.
- Follow base model terms of use.