Instructions to use FutureMa/qwen35-4b-lora-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FutureMa/qwen35-4b-lora-sft with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("/ephemeral/models/Qwen3.5-4B")
model = PeftModel.from_pretrained(base_model, "FutureMa/qwen35-4b-lora-sft")

Transformers

How to use FutureMa/qwen35-4b-lora-sft with Transformers:

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

pipe = pipeline("text-generation", model="FutureMa/qwen35-4b-lora-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("FutureMa/qwen35-4b-lora-sft", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FutureMa/qwen35-4b-lora-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FutureMa/qwen35-4b-lora-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FutureMa/qwen35-4b-lora-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FutureMa/qwen35-4b-lora-sft

SGLang

How to use FutureMa/qwen35-4b-lora-sft 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 "FutureMa/qwen35-4b-lora-sft" \
    --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": "FutureMa/qwen35-4b-lora-sft",
		"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 "FutureMa/qwen35-4b-lora-sft" \
        --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": "FutureMa/qwen35-4b-lora-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FutureMa/qwen35-4b-lora-sft with Docker Model Runner:
```
docker model run hf.co/FutureMa/qwen35-4b-lora-sft
```

Qwen3.5-4B LoRA SFT (checkpoint-971)

LoRA adapter fine-tuned on stepfun-ai/Step-3.5-Flash-SFT using Axolotl on a single NVIDIA H100 PCIe 80GB.

This is checkpoint-971 (epoch=1.0), the best checkpoint by eval loss (0.787).

Training Details


Base model	Qwen/Qwen3.5-4B
Dataset	stepfun-ai/Step-3.5-Flash-SFT (chunk_0, ~14.5k samples)
LoRA rank	128
LoRA alpha	256
Trainable params	195M / 4.73B (4.13%)
Best eval loss	0.787 (epoch 1.0)
Hardware	1× H100 PCIe 80GB
Training time	~3 hours

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel
import torch

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-4B", dtype=torch.bfloat16, device_map="cuda")
tokenizer = AutoTokenizer.from_pretrained("FutureMa/qwen35-4b-lora-sft")
model = PeftModel.from_pretrained(base, "FutureMa/qwen35-4b-lora-sft")

messages = [{"role": "user", "content": "Explain what a lambda function is in Python."}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=False)
inputs = tokenizer(text, return_tensors="pt").to("cuda")
out = model.generate(**inputs, max_new_tokens=512, do_sample=False)
print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))

Framework versions

PEFT 0.18.1
Axolotl (latest)

Downloads last month: 1

Model tree for FutureMa/qwen35-4b-lora-sft

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Adapter

(361)

this model