UOPD-Qwen2.5-3B-Instruct-ALFWorld
Final UOPD student checkpoint trained on ALFWorld with the frozen teacher
langfeng01/GiGPO-Qwen2.5-7B-Instruct-ALFWorld.
Usage
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "Wenboz/UOPD-Qwen2.5-3B-Instruct-ALFWorld"
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained(model_id)
Training configuration
| Setting | Value |
|---|---|
| Student initialization | Qwen/Qwen2.5-3B-Instruct |
| Teacher | langfeng01/GiGPO-Qwen2.5-7B-Instruct-ALFWorld |
| Training steps | 250 |
| Rollout / training batch | 16 / 64 |
| Environment step limit | 50 |
| Max prompt / response tokens | 2,048 / 512 |
| Optimizer | AdamW, learning rate 1e-6 |
| Target intervention rate | linear 0.30 → 0.05 over the first 120 training steps, then 0.05 |
| Triggered-turn loss | Plain SFT, weight 1.0 |
| Teacher takeover | Enabled |