---
library_name: transformers
license: llama2
---

# Haary/haryra-7b-id
<!-- markdownlint-disable MD041 -->

<!-- header start -->
<!-- 200823 -->
<div style="margin-left: auto; margin-right: auto">
<img src="https://cdn.pixabay.com/photo/2023/08/12/13/22/peacock-8185593_960_720.png" alt="merak" style="width: 300px; margin:auto">
</div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->

[Haary/haryra-7b-id](https://huggingface.co/Haary/haryra-7b-id) is QLoRA quantized version of [Ichsan2895/Merak-7B-v3](https://huggingface.co/Ichsan2895/Merak-7B-v3)

### Install the necessary packages

Requires: Transformers from source - only needed for versions <= v4.34.

```shell
# Install transformers from source - only needed for versions <= v4.34
!pip install git+https://github.com/huggingface/transformers.git
!pip install accelerate
```

### Example Python code

```python
import torch
from transformers import pipeline

pipe = pipeline("text-generation", model="Haary/haryra-7b-id", torch_dtype=torch.bfloat16, device_map="auto")

# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
messages = [
    {
        "role": "system",
        "content": "Anda adalah chatbot ramah yang selalu merespons dengan singkat dan jelas",
    },
    {"role": "user", "content": "Apa bedanya antara raspberry pi dan esp32?"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```


## Credits
[Ichsan2895/Merak-7B-v3](https://huggingface.co/Ichsan2895/Merak-7B-v3) for base model.


## image source
pixabay.com