|
|
--- |
|
|
license: apache-2.0 |
|
|
--- |
|
|
|
|
|
# S1-Base-1.5-8B-128K |
|
|
|
|
|
[中文版](./README_zh.md) ｜ [English](./README.md) |
|
|
|
|
|
## Model Introduction |
|
|
|
|
|
This repository contains the S1-Base-1.5-8B-128K general scientific large language model, developed through post-training (SFT+GRPO) based on the scientific foundation model [S1-Base](https://huggingface.co/collections/ScienceOne-AI/s1-base). This model maintains scientific reasoning capabilities while significantly enhancing long context understanding and reasoning abilities, as well as complex instruction following in scientific research scenarios. The model supports a context length of 128k. |
|
|
|
|
|
## Model Weights |
|
|
|
|
|
The S1-Base-1.5-8B-128K model is open-sourced under the Apache 2.0 license. You can download the model weights from our [Huggingface](https://huggingface.co/ScienceOne-AI/S1-Base-1.5-8B-128K) or [ModelScope](https://modelscope.cn/models/ScienceOne-AI/S1-Base-1.5-8B-128K). |
|
|
|
|
|
|
|
|
| Model Name | Huggingface Link | ModelScope Link | |
|
|
|-------------|-------------------------------------|-------------------------------------| |
|
|
|S1-Base-8B | [Download](https://huggingface.co/ScienceOne-AI/S1-Base-1.5-8B-128K) | [Download](https://modelscope.cn/models/ScienceOne-AI/S1-Base-1.5-8B-128K) | |
|
|
|
|
|
## Model Evaluation |
|
|
|
|
|
|
|
|
To comprehensively validate the capabilities of S1-Base-1.5-128K, we conducted systematic evaluations across three core competencies: long context ability, instruction following ability, and scientific reasoning ability. The results are shown in the table below. |
|
|
|
|
|
| Benchmark | S1-Base-1.5-8B-128K | S1-Base-8B | Qwen3-8B | Intern-S1-mini | GLM-Z1-9B-0414 | |
|
|
|---|---|---|---|---|---| |
|
|
| CLongEval | **36.18** | 27.51 | 33.62 | 32.82 | 25.71 | |
|
|
| InfiniteBench | **35.57** | 27.62 | 34.41 | 30.42 | 29.58 | |
|
|
| IFEval | **87.06** | 70.42 | 85.00 | 83.00 | 78.93 | |
|
|
| GPQA | **70.33** | 63.01 | 60.86 | 65.97 | 55.81 | |
|
|
| ChemBench | 61.59 | **62.74** | 57.79 | 57.54 | 55.85 | |
|
|
| LLM-MSE | 83.63 | **88.50** | 83.51 | 78.65 | 80.97 | |
|
|
| LAB bench | 37.54 | **37.63** | 26.52 | 29.11 | 29.89 | |
|
|
| AIME2024 | 77.92 | 75.42 | 74.60 | **85.00** | 79.37 | |
|
|
| LiveMathBench | **86.72** | 82.81 | 77.00 | **86.72** | 82.82 | |
|
|
|
|
|
**Key Highlights:** |
|
|
- 📜 **Enhanced Long Context Reasoning**: The model leads among base models and similar-sized models on public long-context benchmarks such as CLongEval and InfiniteBench, with significant improvements in custom long-text evaluations for real-world scenarios involving papers and web pages. |
|
|
- 🎯 **Improved Complex Instruction Following**: Built with a scientific literature instruction following task system covering four major categories—document understanding, structured generation, information extraction, and chart comprehension—combined with multi-dimensional constraints including length, format, and content. The model maintains leadership on benchmarks like IFEval. |
|
|
- 🔬 **Stable Scientific Reasoning Capability**: The model shows significant advantages on GPQA, a comprehensive scientific capability evaluation benchmark covering biology, physics, and chemistry. Performance on other scientific task evaluation benchmarks remains stable without significant fluctuations due to context expansion. |
|
|
- 👍 **User Feedback Data Flywheel**: Continuously optimizes model performance and user experience in real-world scenarios by incorporating user likes and dislikes feedback from the [ScienceOne](https://scienceone.cn) platform. |
|
|
|
|
|
## Deployment |
|
|
|
|
|
We recommend using [vLLM](https://github.com/vllm-project/vllm) to deploy S1-Base for efficient inference and OpenAI-compatible API services. |
|
|
|
|
|
**Quick start command example:** |
|
|
```bash |
|
|
pip install vllm |
|
|
vllm serve <your_s1_model_path> --served-model-name s1-base-1.5-8b-128k |
|
|
``` |
|
|
The API request and response formats are basically consistent with OpenAI. Please refer to the official vLLM documentation for details. |
|
|
|
|
|
**Generate responses using OpenAI Python SDK:** |
|
|
```python |
|
|
from openai import OpenAI |
|
|
|
|
|
client = OpenAI(base_url="http://localhost:8000/v1", api_key="") |
|
|
resp = client.chat.completions.create( |
|
|
model="s1-base-1.5-8b-128k", |
|
|
messages=[{"role": "user", "content": "hi"}] |
|
|
) |
|
|
print(resp.choices[0].message.content) |
|
|
``` |
|
|
|
|
|
**Generate responses using CURL:** |
|
|
```bash |
|
|
curl -X POST http://localhost:8000/v1/chat/completions -d '{"model": "s1-base-1.5-8b-128k", "messages":[{"role":"user", "content": "hi"}], "skip_special_tokens": false}' -H "Content-Type: application/json" |
|
|
``` |
