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 (A100 80GB Optimized)

Base model: Qwen/Qwen2.5-7B-Instruct
GPU: A100 80GB (TF32 enabled, Flash Attention 2)
Method: LoRA (full precision base, bf16)
Datasets: ALFWorld v5 + DBBench v4 (combined ~5,500 samples)
Max sequence length: 8192
Epochs: 1
Learning rate: 2e-06
LoRA: r=64, alpha=128, dropout=0.05
Effective batch size: 8 x 2 = 16

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.bfloat16,
    device_map="auto",
    attn_implementation="flash_attention_2",
)
model = PeftModel.from_pretrained(model, adapter)

Sources & Terms (IMPORTANT)

Training data:

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

Dataset License: MIT License. Users must comply with the MIT license and the base model's original terms of use.

legoskier/Qwen2.5-7B-agent-trajectory-lora_5_2

Qwen2.5-7B-agent-trajectory-lora_5_2

Training Objective

Training Configuration (A100 80GB Optimized)

Usage

Sources & Terms (IMPORTANT)

legoskier/
Qwen2.5-7B-agent-trajectory-lora_5_2