Instructions to use Styl4/shopping-agent-rl-sft-2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Styl4/shopping-agent-rl-sft-2b with Transformers:

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

pipe = pipeline("image-text-to-text", model="Styl4/shopping-agent-rl-sft-2b")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Styl4/shopping-agent-rl-sft-2b")
model = AutoModelForMultimodalLM.from_pretrained("Styl4/shopping-agent-rl-sft-2b", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Styl4/shopping-agent-rl-sft-2b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Styl4/shopping-agent-rl-sft-2b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Styl4/shopping-agent-rl-sft-2b",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Styl4/shopping-agent-rl-sft-2b

SGLang

How to use Styl4/shopping-agent-rl-sft-2b 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 "Styl4/shopping-agent-rl-sft-2b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Styl4/shopping-agent-rl-sft-2b",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "Styl4/shopping-agent-rl-sft-2b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Styl4/shopping-agent-rl-sft-2b",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use Styl4/shopping-agent-rl-sft-2b with Docker Model Runner:
```
docker model run hf.co/Styl4/shopping-agent-rl-sft-2b
```

Shopping Agent RL — Curriculum SFT C (2B)

Merged Qwen3.5-2B weights after cumulative A/B/C curriculum SFT with action-only supervision. Teacher trajectories were generated with DeepSeek V4 Flash from 1,192 unique tasks. Final200 Clean strict success with the enhanced execution harness: 130/200 (65%).

Format and download

Standalone Hugging Face merged model, approximately 4.45 GB including tokenizer and configuration. No separate SFT adapter is required.

from huggingface_hub import snapshot_download
model_dir = snapshot_download("Styl4/shopping-agent-rl-sft-2b")

Use the Transformers revision pinned in the code repository; the saved architecture is Qwen3_5ForConditionalGeneration. The checkpoint was saved with Transformers 5.15.0.dev0. Example loading (not a newly executed evaluation):

import torch
from transformers import Qwen3_5ForConditionalGeneration, AutoTokenizer
model = Qwen3_5ForConditionalGeneration.from_pretrained(model_dir, dtype=torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_dir)

Training

Cumulative curriculum manifests: A 256/28, B 799/88, C 1073/119 train/validation tasks. Historical C preprocessing produced 1069/118 usable samples. Action-only LoRA SFT used rank 16, alpha 32, BF16, and maximum sequence length 24,576; LoRA was merged after each stage.

Evaluation scope

Results use the fixed Final200 Clean task list, greedy decoding (temperature 0, top_p 1), explicit product-detail tools, and a 35-step limit. Strict Reward v3 success requires a completed purchase, valid reward, and no infrastructure-invalid outcome. These are Reward-panel results, not completed dual-LLM-Judge scores. RL evaluation also includes a search-serialization fix, so the 4 percentage-point difference is not an isolated RL effect.

Intended use

Research on Chinese shopping policy post-training and simulated tool use in ShopSimulator. Use the task prompts, tools, and execution harness from the code repository; these weights alone do not provide a shopping application. General chat, real purchases, and multimodal performance were not evaluated in this project.

Code and license

Code, environment setup, training configuration, and evaluation protocol: Styleofm3/shopping-agent-rl.

Derived from Qwen/Qwen3.5-2B, licensed under Apache-2.0. Model weights retain Apache-2.0; the project code uses MIT. See LICENSE in this model repository.

Downloads last month: 14

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for Styl4/shopping-agent-rl-sft-2b

Base model

Qwen/Qwen3.5-2B-Base

Finetuned

Qwen/Qwen3.5-2B

Finetuned

(500)

this model

Finetunes

1 model