Instructions to use Phonsiri/gemma-2-2b-SFT-Reasoning-full-Model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Phonsiri/gemma-2-2b-SFT-Reasoning-full-Model with Transformers:

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

pipe = pipeline("text-generation", model="Phonsiri/gemma-2-2b-SFT-Reasoning-full-Model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Phonsiri/gemma-2-2b-SFT-Reasoning-full-Model")
model = AutoModelForCausalLM.from_pretrained("Phonsiri/gemma-2-2b-SFT-Reasoning-full-Model")
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

vLLM

How to use Phonsiri/gemma-2-2b-SFT-Reasoning-full-Model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Phonsiri/gemma-2-2b-SFT-Reasoning-full-Model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Phonsiri/gemma-2-2b-SFT-Reasoning-full-Model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Phonsiri/gemma-2-2b-SFT-Reasoning-full-Model

SGLang

How to use Phonsiri/gemma-2-2b-SFT-Reasoning-full-Model 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 "Phonsiri/gemma-2-2b-SFT-Reasoning-full-Model" \
    --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": "Phonsiri/gemma-2-2b-SFT-Reasoning-full-Model",
		"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 "Phonsiri/gemma-2-2b-SFT-Reasoning-full-Model" \
        --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": "Phonsiri/gemma-2-2b-SFT-Reasoning-full-Model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Phonsiri/gemma-2-2b-SFT-Reasoning-full-Model with Docker Model Runner:
```
docker model run hf.co/Phonsiri/gemma-2-2b-SFT-Reasoning-full-Model
```

Gemma-2-2B SFT Reasoning Model

A supervised fine-tuned version of google/gemma-2-2b, trained to produce structured chain-of-thought reasoning on mathematical and logical problems.

Model Lineage: This SFT model serves as the foundation for downstream training: Phonsiri/gemma-2-2b-GRPO-Reasoning-full

Model Highlights

This model was trained to explicitly separate its reasoning process from its final answer, using a structured output format. It learns the syntax and structure of chain-of-thought reasoning before any reinforcement signal is applied.

Output Format:

Section	Tag	Description
Chain-of-Thought	`<reasoning> ... </reasoning>`	Step-by-step internal reasoning
Final Answer	`<answer> ... </answer>`	Concise final answer

Training Details

Base Model

Fine-tuned from google/gemma-2-2b-it using full parameter fine-tuning (no LoRA/PEFT).

Datasets

Training data was combined from the following sources:

Dataset	Type
`nohurry/Opus-4.6-Reasoning-3000x-filtered`	HuggingFace — Reasoning
`math_combined_2566_2567.json`	Local — Thai math problems
`problems_1_5.json`	Local — Math problems
`problems_6_10.json`	Local — Math problems
`problems_101_125.json`	Local — Math problems
`combined.json`	Local — Combined problems
`all_solutions.json`	Local — Solutions

Hyperparameters

Parameter	Value
Epochs	3
Learning Rate	2e-5
LR Scheduler	Cosine
Max Seq Length	8192
Batch Size (per device)	4
Gradient Accumulation	4
Effective Batch Size	16
Warmup Ratio	0.1
Weight Decay	0.01
Precision	bfloat16
Gradient Checkpointing	Yes
Attention	SDPA
Optimizer	AdamW

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
import torch

model_id = "Phonsiri/gemma-2-2b-SFT-Reasoning-full-Model"

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

system_prompt = (
    "You are a helpful assistant. Please reason step by step, "
    "and put your thoughts within <reasoning> and </reasoning> tags, "
    "and your final answer within <answer> and </answer> tags."
)
prompt = "Solve for x: 3x + 5 = 20"

messages = [{"role": "user", "content": f"{system_prompt}\n\n{prompt}"}]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=False)

with torch.no_grad():
    model.generate(
        **inputs,
        streamer=streamer,
        max_new_tokens=4096,
        temperature=0.6,
        top_p=0.9,
        repetition_penalty=1.1,
    )

Example Output

<reasoning>
We need to isolate x on one side of the equation.

Step 1: Subtract 5 from both sides.
  3x + 5 - 5 = 20 - 5
  3x = 15

Step 2: Divide both sides by 3.
  x = 15 / 3
  x = 5
</reasoning>

<answer>
x = 5
</answer>

Acknowledgements

Authors:

Phonsiri Thabunsri — @Phonsiriwillbejommarn
CYP777 — @CYP777

Project Advisor:

Supaporn Bunrit, Ph.D. — Suranaree University of Technology

Institutions & Credits:

Suranaree University of Technology (SUT) — Research support and computing resources
Google DeepMind — Open-weights Gemma 2 model

Downloads last month: 3

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for Phonsiri/gemma-2-2b-SFT-Reasoning-full-Model

Base model

google/gemma-2-2b

Finetuned

(524)

this model

Finetunes

1 model

Phonsiri
/

gemma-2-2b-SFT-Reasoning-full-Model