Instructions to use y-ohtani/qwen3-4b-agent-sft-true with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use y-ohtani/qwen3-4b-agent-sft-true with Transformers:

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

pipe = pipeline("text-generation", model="y-ohtani/qwen3-4b-agent-sft-true")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("y-ohtani/qwen3-4b-agent-sft-true")
model = AutoModelForMultimodalLM.from_pretrained("y-ohtani/qwen3-4b-agent-sft-true")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use y-ohtani/qwen3-4b-agent-sft-true with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "y-ohtani/qwen3-4b-agent-sft-true"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "y-ohtani/qwen3-4b-agent-sft-true",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/y-ohtani/qwen3-4b-agent-sft-true

SGLang

How to use y-ohtani/qwen3-4b-agent-sft-true 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 "y-ohtani/qwen3-4b-agent-sft-true" \
    --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": "y-ohtani/qwen3-4b-agent-sft-true",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "y-ohtani/qwen3-4b-agent-sft-true" \
        --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": "y-ohtani/qwen3-4b-agent-sft-true",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use y-ohtani/qwen3-4b-agent-sft-true with Docker Model Runner:
```
docker model run hf.co/y-ohtani/qwen3-4b-agent-sft-true
```

Qwen3-4B-Agent-SFT-True

This repository contains a full fine-tuned model (not LoRA adapter) based on Qwen3-4B-Instruct-2507, trained with multi-turn agentic SFT using the Open-AgentRL framework (verl FSDP SFT Trainer).

Training Configuration

Parameter	Value
Base model	`Qwen/Qwen3-4B-Instruct-2507`
Method	Full fine-tuning (FSDP, bfloat16)
Max sequence length	32,768
Epochs	10
Train batch size	16
Micro batch size per GPU	1
Truncation	right
Trainer	`verl.trainer.fsdp_sft_trainer`

Dataset

Name: Gen-Verse/Open-AgentRL-SFT-3K
Samples: 3,000 multi-turn conversations
Source: Original Open-AgentRL SFT dataset (real End-to-End agentic trajectories)

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "y-ohtani/qwen3-4b-agent-sft-true"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

messages = [
    {"role": "user", "content": "Solve the equation x^2 - 5x + 6 = 0 step by step."}
]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=2048)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Sources & Terms

Component	Source	License
Base model	Qwen/Qwen3-4B-Instruct-2507	Apache-2.0
SFT dataset	Gen-Verse/Open-AgentRL-SFT-3K	--
Training framework	Open-AgentRL (verl)	Apache-2.0

Users must comply with the base model license and dataset terms.

Downloads last month: 16

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for y-ohtani/qwen3-4b-agent-sft-true

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

(1748)

this model

y-ohtani
/

qwen3-4b-agent-sft-true