| | --- |
| | license: apache-2.0 |
| | base_model: |
| | - HuggingFaceTB/SmolLM2-360M-Instruct |
| | language: |
| | - en |
| | pipeline_tag: text-generation |
| | tags: |
| | - safetensors |
| | - onnx |
| | - transformers.js |
| | --- |
| | |
| | # 🌞 Solara — summerstars/Solara |
| |
|
| | ## **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** |
| |
|
| | **Solara** is a lightweight, instruction-tuned language model based on [`HuggingFaceTB/SmolLM2-360M-Instruct`](https://huggingface.co/HuggingFaceTB/SmolLM2-360M-Instruct). |
| | It was developed by a high school student using Google Colab with a T4 GPU. |
| | Despite its compact size, Solara delivers quick responses and handles everyday tasks efficiently. |
| |
|
| | **Solara(ソララ)** は、[`HuggingFaceTB/SmolLM2-360M-Instruct`](https://huggingface.co/HuggingFaceTB/SmolLM2-360M-Instruct) をベースとした軽量な指示応答型言語モデルです。 |
| | Google Colab(T4 GPU)を使用して高校生が開発しました。 |
| | 小型ながら、日常のタスクや会話を効率的かつ高速に処理します。 |
| |
|
| | --- |
| |
|
| | ## 📌 Model Details / モデル詳細 |
| |
|
| | - **Base Model / ベースモデル**: HuggingFaceTB/SmolLM2-360M-Instruct |
| | - **Parameters / パラメータ数**: 360M |
| | - **Architecture / アーキテクチャ**: Decoder-only Transformer / デコーダ専用トランスフォーマー |
| | - **Languages / 対応言語**: English / 英語 |
| | - **License / ライセンス**: Apache 2.0 |
| |
|
| | --- |
| |
|
| | ## 🚀 Use Cases / 主な用途 |
| |
|
| | - Lightweight chatbots / 軽量チャットボット |
| | - Inference on CPUs or mobile devices / CPU・モバイル端末での推論 |
| | - Educational or hobbyist projects / 教育・趣味用途 |
| | - Instruction-following tasks / 指示応答タスク |
| |
|
| | --- |
| |
|
| | ## 🛠️ How to Use / 使用方法 |
| |
|
| | ```python |
| | from transformers import AutoTokenizer, AutoModelForCausalLM |
| | |
| | model_name = "summerstars/Solara" |
| | |
| | tokenizer = AutoTokenizer.from_pretrained(model_name) |
| | model = AutoModelForCausalLM.from_pretrained(model_name) |
| | |
| | prompt = "Please explain black holes in simple terms." |
| | inputs = tokenizer(prompt, return_tensors="pt") |
| | outputs = model.generate(**inputs, max_new_tokens=128) |
| | |
| | # Print the result / 結果を表示 |
| | print(tokenizer.decode(outputs[0], skip_special_tokens=True)) |