Instructions to use uchkw/qwen3-4b-instruct-2507-sft-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use uchkw/qwen3-4b-instruct-2507-sft-v1 with Transformers:

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

pipe = pipeline("text-generation", model="uchkw/qwen3-4b-instruct-2507-sft-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("uchkw/qwen3-4b-instruct-2507-sft-v1")
model = AutoModelForCausalLM.from_pretrained("uchkw/qwen3-4b-instruct-2507-sft-v1", device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use uchkw/qwen3-4b-instruct-2507-sft-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "uchkw/qwen3-4b-instruct-2507-sft-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "uchkw/qwen3-4b-instruct-2507-sft-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/uchkw/qwen3-4b-instruct-2507-sft-v1

SGLang

How to use uchkw/qwen3-4b-instruct-2507-sft-v1 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 "uchkw/qwen3-4b-instruct-2507-sft-v1" \
    --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": "uchkw/qwen3-4b-instruct-2507-sft-v1",
		"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 "uchkw/qwen3-4b-instruct-2507-sft-v1" \
        --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": "uchkw/qwen3-4b-instruct-2507-sft-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use uchkw/qwen3-4b-instruct-2507-sft-v1 with Docker Model Runner:
```
docker model run hf.co/uchkw/qwen3-4b-instruct-2507-sft-v1
```

qwen3-4b-instruct-2507-sft-v1

This repository provides a merged full model produced by supervised fine-tuning for ALFWorld-oriented action selection.

Training Objective

Improve strict action selection reliability for ALFWorld-style prompts where the model must output one exact action line from AVAILABLE ACTIONS.

Training Configuration

Method: SFT (Unsloth LoRA) + merge to full model
Base model ID: Qwen/Qwen3-4B-Instruct-2507
LoRA: r=16, alpha=32, dropout=0.05
LoRA target modules: q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj
Max sequence length: 4096
Max steps: 350
Epochs: 1
Learning rate: 1.0e-6
Per-device train batch size: 1
Per-device eval batch size: 2
Gradient accumulation steps: 32
Effective global batch size: 32
Warmup ratio: 0.03
Weight decay: 0.01
Eval/Save steps: 50 / 50

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "uchkw/qwen3-4b-instruct-2507-sft-v1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

Training Data / Sources & License (IMPORTANT)

Primary source dataset:
- u-10bei/sft_alfworld_trajectory_dataset_v5
Data construction policy:
- Converted trajectories into strict chat-style supervision with one-line action targets (ACTION: ...).
- Trained with exact action matching against candidate action lists to improve action validity.
- Added synthetic correction-style augmentation for common formatting and target-selection errors.
Dataset scale (used for this merged model):
- Train samples: 35950
- Validation samples: 1892
- Action coverage was balanced to avoid over-concentration on a few verbs.
Sequence-length check:
- No truncation observed at max_seq_length=4096.
Compliance:
- Follow the source dataset license on each dataset card.
- Follow base model terms of use.

Downloads last month: 7

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for uchkw/qwen3-4b-instruct-2507-sft-v1

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

(2133)

this model

uchkw
/

qwen3-4b-instruct-2507-sft-v1