Instructions to use summerstars/SolaraV2-coder-0509 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use summerstars/SolaraV2-coder-0509 with Transformers:

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

pipe = pipeline("text-generation", model="summerstars/SolaraV2-coder-0509")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("summerstars/SolaraV2-coder-0509")
model = AutoModelForCausalLM.from_pretrained("summerstars/SolaraV2-coder-0509")
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

vLLM

How to use summerstars/SolaraV2-coder-0509 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "summerstars/SolaraV2-coder-0509"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "summerstars/SolaraV2-coder-0509",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/summerstars/SolaraV2-coder-0509

SGLang

How to use summerstars/SolaraV2-coder-0509 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 "summerstars/SolaraV2-coder-0509" \
    --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": "summerstars/SolaraV2-coder-0509",
		"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 "summerstars/SolaraV2-coder-0509" \
        --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": "summerstars/SolaraV2-coder-0509",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use summerstars/SolaraV2-coder-0509 with Docker Model Runner:
```
docker model run hf.co/summerstars/SolaraV2-coder-0509
```

🌞 SolaraV2 — `summerstars/SolaraV2`

📅 Version 0509（2025-05-09）
This is the 0509 release of SolaraV2.

✨ Created by a High School Student | Built on Google Colab (T4 GPU)

🌸 高校生によって開発 | Google Colab（T4 GPU）で作成

SolaraV2 is an upgraded version of the original Solara — a lightweight, instruction-tuned language model based on HuggingFaceTB/SmolLM2-360M-Instruct.
This version is trained on a larger and more diverse dataset, including basic math-related samples, improving its ability to handle both casual conversations and educational tasks.
All development was conducted by a high school student using Google Colab and a T4 GPU.

SolaraV2（ソララV2） は、オリジナルの Solara モデルを改良した軽量の言語モデルで、HuggingFaceTB/SmolLM2-360M-Instruct をベースにしています。
本バージョンでは、より大規模かつ多様なデータセット（数学系データを含む）で学習を行い、日常会話から教育的な質問まで幅広く対応できるようになりました。
開発はすべて、高校生が Google Colab（T4 GPU） 上で行いました。

📌 Model Details | モデル詳細

Feature / 特徴	Description / 説明
Base Model	`HuggingFaceTB/SmolLM2-360M-Instruct`
Parameters	360M
Architecture	Decoder-only Transformer
Language	English / 英語
License	Apache 2.0
Training Additions	Basic math, factual Q&A / 基本数学・事実ベースのデータ追加

🚀 Use Cases | 主な用途

🤖 Lightweight chatbots / 軽量チャットボット
📱 Inference on CPUs or mobile devices / CPUやモバイル端末での推論
📚 Educational or hobbyist projects / 教育・趣味向けプロジェクト
🧾 Instruction-following tasks / 指示応答タスク
➗ Basic math questions / 基本的な数学問題への対応

🛠️ How to Use | 使用方法

from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "summerstars/SolaraV2-coder-0509"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

prompt = "What is 15 * 4?"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=64)

# Print the result / 結果を表示
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Downloads last month: -

Safetensors

Model size

0.4B params

Tensor type

F32

Model tree for summerstars/SolaraV2-coder-0509

Base model

HuggingFaceTB/SmolLM2-360M

Quantized

HuggingFaceTB/SmolLM2-360M-Instruct

Finetuned

(143)

this model

🌞 SolaraV2 — summerstars/SolaraV2