---
license: mit
language:
- ja
library_name: transformers
pipeline_tag: text-generation
tags:
- japanese
- llama-2
- instruction-tuning
---

# Stockmark-13b-instruct

**Stockmark-13b-instruct** is an instruction-tuned version of [Stockmark-13b](https://huggingface.co/stockmark/stockmark-13b), a 13 billion parameter Japanese LLM. This model is developed by [Stockmark Inc.](https://stockmark.co.jp/)

We used data (2023/11/03 version) from [Project of Development of Japanese Instruction data for LLM](https://liat-aip.sakura.ne.jp/wp/llm%E3%81%AE%E3%81%9F%E3%82%81%E3%81%AE%E6%97%A5%E6%9C%AC%E8%AA%9E%E3%82%A4%E3%83%B3%E3%82%B9%E3%83%88%E3%83%A9%E3%82%AF%E3%82%B7%E3%83%A7%E3%83%B3%E3%83%87%E3%83%BC%E3%82%BF%E4%BD%9C%E6%88%90/) for instruction tuning.

Please see our [blog](https://tech.stockmark.co.jp/blog/202311_stockmark_13b_instruct/) for more details.

## How to use

```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("stockmark/stockmark-13b-instruct", device_map="auto", torch_dtype=torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained("stockmark/stockmark-13b-instruct")

instruction = "自然言語処理とは？"

prompt = f"""### Input:
{instruction}

### Output:
"""

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    tokens = model.generate(
        **inputs,
        max_new_tokens=128,
        do_sample=True,
        temperature=0.7
    )
    
output = tokenizer.decode(tokens[0], skip_special_tokens=True)
print(output)
```

## Training dataset
[Project of Development of Japanese Instruction data for LLM](https://liat-aip.sakura.ne.jp/wp/llm%E3%81%AE%E3%81%9F%E3%82%81%E3%81%AE%E6%97%A5%E6%9C%AC%E8%AA%9E%E3%82%A4%E3%83%B3%E3%82%B9%E3%83%88%E3%83%A9%E3%82%AF%E3%82%B7%E3%83%A7%E3%83%B3%E3%83%87%E3%83%BC%E3%82%BF%E4%BD%9C%E6%88%90/)

## License
MIT

## Developed by
[Stockmark Inc.](https://stockmark.co.jp/)

## Author
[Takahiro Omi](https://huggingface.co/omitakahiro)