Instructions to use wckwan/WebShop-Qwen3-8B-Adaptive-Random with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wckwan/WebShop-Qwen3-8B-Adaptive-Random with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="wckwan/WebShop-Qwen3-8B-Adaptive-Random")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("wckwan/WebShop-Qwen3-8B-Adaptive-Random", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use wckwan/WebShop-Qwen3-8B-Adaptive-Random with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wckwan/WebShop-Qwen3-8B-Adaptive-Random"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wckwan/WebShop-Qwen3-8B-Adaptive-Random",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/wckwan/WebShop-Qwen3-8B-Adaptive-Random

SGLang

How to use wckwan/WebShop-Qwen3-8B-Adaptive-Random with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "wckwan/WebShop-Qwen3-8B-Adaptive-Random" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wckwan/WebShop-Qwen3-8B-Adaptive-Random",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "wckwan/WebShop-Qwen3-8B-Adaptive-Random" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wckwan/WebShop-Qwen3-8B-Adaptive-Random",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use wckwan/WebShop-Qwen3-8B-Adaptive-Random with Docker Model Runner:
```
docker model run hf.co/wckwan/WebShop-Qwen3-8B-Adaptive-Random
```

WebShop-Qwen3-8B-Adaptive-Random

A Qwen/Qwen3-8B policy trained as a multi-turn search agent (Search-R1 style) with Process-GRPO: a process reward model (Olmo-3-7B-Think verifier) scores each turn, with per-(group, turn-position) advantage normalization and verifier prompts that include the retrieved tool responses and the gold answer.

The model at the repository root is the final policy (training step 200). Intermediate checkpoints are provided under step_<STEP>/ subfolders.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

# Final model (repo root)
model = AutoModelForCausalLM.from_pretrained("wckwan/WebShop-Qwen3-8B-Adaptive-Random")
tokenizer = AutoTokenizer.from_pretrained("wckwan/WebShop-Qwen3-8B-Adaptive-Random")

# An intermediate checkpoint
model_step = AutoModelForCausalLM.from_pretrained("wckwan/WebShop-Qwen3-8B-Adaptive-Random", subfolder="step_20")

Checkpoints

Root: final policy at step 200.

step_20/ — intermediate checkpoint at training step 20
step_40/ — intermediate checkpoint at training step 40
step_60/ — intermediate checkpoint at training step 60
step_80/ — intermediate checkpoint at training step 80
step_100/ — intermediate checkpoint at training step 100
step_120/ — intermediate checkpoint at training step 120
step_140/ — intermediate checkpoint at training step 140
step_160/ — intermediate checkpoint at training step 160
step_180/ — intermediate checkpoint at training step 180

Training summary (step 200)

Process-reward score mean ≈ 0.93
Searches per trajectory ≈ 2.6 (non-collapsed, diverse multi-search policy)
Training-batch accuracy ≈ 0.49

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for wckwan/WebShop-Qwen3-8B-Adaptive-Random

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Finetuned

(2072)

this model