Instructions to use thealper2/qwen3-0.6b-reasoning-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thealper2/qwen3-0.6b-reasoning-sft with Transformers:

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

pipe = pipeline("text-generation", model="thealper2/qwen3-0.6b-reasoning-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("thealper2/qwen3-0.6b-reasoning-sft")
model = AutoModelForCausalLM.from_pretrained("thealper2/qwen3-0.6b-reasoning-sft", 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 thealper2/qwen3-0.6b-reasoning-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thealper2/qwen3-0.6b-reasoning-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": "thealper2/qwen3-0.6b-reasoning-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/thealper2/qwen3-0.6b-reasoning-sft

SGLang

How to use thealper2/qwen3-0.6b-reasoning-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 "thealper2/qwen3-0.6b-reasoning-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": "thealper2/qwen3-0.6b-reasoning-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 "thealper2/qwen3-0.6b-reasoning-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": "thealper2/qwen3-0.6b-reasoning-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use thealper2/qwen3-0.6b-reasoning-sft with Docker Model Runner:
```
docker model run hf.co/thealper2/qwen3-0.6b-reasoning-sft
```

qwen3-0.6b-reasoning-sft

Full-parameter supervised fine-tune of Qwen/Qwen3-0.6B on Kenshiii/minimax-m3-reasoning-traces (data/chat.jsonl).

Model details


Base model	`Qwen/Qwen3-0.6B` @ `c1899de289a04d12100db370d81485cdf75e47ca`
Method	Full fine-tuning (TRL `SFTTrainer`)
Parameters	596,049,920 total, 596,049,920 trained
Precision	fp32 master weights, bfloat16 autocast
Training sequence length	2048 tokens
Chat template	Qwen3 template, unchanged
Reasoning format	Qwen3 native `<think>…</think>` block, followed by the final answer

Training data

Source: Kenshiii/minimax-m3-reasoning-traces @ 157ed14aecdb6e0fa0a09ea5981b45048cca2f3d, file data/chat.jsonl (single file; the other files in the repo are re-formattings of the same traces).
Format: system + user → assistant turn with the dataset's <thinking> trace mapped to Qwen3's reasoning_content (rendered as <think>), then the final answer. Loss on assistant tokens only.
Split (seed 42, domain-stratified, near-duplicate prompts grouped at 5-gram Jaccard ≥ 0.8): train 847 / validation 106 / test 106.
Truncation: 17 training examples exceeded 2048 tokens; the end of the reasoning trace was shortened, the final answer kept.

Training procedure

Hyperparameter	Value
Epochs (max)	3
Learning rate	2e-05
LR scheduler	cosine, warmup ratio 0.05
Weight decay	0.01
Max grad norm	1.0
Effective batch size	16 (1 × 16 accumulation)
Optimizer	adamw_torch_fused
Gradient checkpointing	True
Checkpoint selection	lowest validation loss
Early stopping patience	3 evaluations (every 10 steps)
Seed	42

Steps: 80 (1.51 epochs), time 10.4 min, peak memory 13.6 GB.
Best validation loss: 1.0698 (checkpoint-40); final logged train loss: 0.8242.
Hardware: NVIDIA GeForce RTX 5060 Ti; CUDA 12.8.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "thealper2/qwen3-0.6b-reasoning-sft"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, dtype="auto", device_map="auto")

messages = [
    {"role": "system", "content": "You are a careful, step-by-step reasoner. For each problem, think through it methodically, then give a final answer."},
    {"role": "user", "content": "Solve x^2 - 7x + 12 = 0 and verify both roots."},
]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
output = model.generate(**inputs, max_new_tokens=2048)
print(tokenizer.decode(output[0, inputs.input_ids.shape[1]:], skip_special_tokens=True))

The model writes its trace inside <think>…</think> and the final answer after </think>. It was trained with the system prompt shown above.

Framework versions

transformers: 5.17.0
trl: 0.24.0
torch: 2.11.0+cu128
datasets: 4.3.0
accelerate: 1.12.0

Downloads last month: 44

Safetensors

Model size

0.6B params

Tensor type

F32

Model tree for thealper2/qwen3-0.6b-reasoning-sft

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-0.6B

Finetuned

(1305)

this model

thealper2
/

qwen3-0.6b-reasoning-sft