How to use from
Docker Model Runner
docker model run hf.co/Wenboz/UOPD-Qwen2.5-3B-Instruct-ALFWorld
Quick Links

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 โ†’ 0.05 over the first 120 training steps, then 0.05
Triggered-turn loss Plain SFT, weight 1.0
Teacher takeover Enabled
Downloads last month
234
Safetensors
Model size
3B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for Wenboz/UOPD-Qwen2.5-3B-Instruct-ALFWorld

Base model

Qwen/Qwen2.5-3B
Finetuned
(1,690)
this model

Collection including Wenboz/UOPD-Qwen2.5-3B-Instruct-ALFWorld