README.md

---
base_model:
- GoToCompany/gemma2-9b-cpt-sahabatai-v1-instruct
- aisingapore/gemma2-9b-cpt-sea-lionv3-instruct
tags:
- merge
- mergekit
license: gemma
language:
- en
- id
- jv
- su
---

# SahabatAI-Lion-9B-TIES-v1

![image/png](https://cdn-uploads.huggingface.co/production/uploads/642b04e4ecec03b44649e318/rJ0ogty-DbLUEH48Ms5lE.png)

Based on some research, when a finetuned model is merged with its base model with TIES method, there is possibility the merged model will achieve better output. 

gmonsoon/SahabatAI-Lion-9B-TIES-v1 is a merge of the following models:
* [GoToCompany/gemma2-9b-cpt-sahabatai-v1-instruct](https://huggingface.co/GoToCompany/gemma2-9b-cpt-sahabatai-v1-instruct)
* [aisingapore/gemma2-9b-cpt-sea-lionv3-instruct](https://huggingface.co/aisingapore/gemma2-9b-cpt-sea-lionv3-instruct)

DEMO Spaces: [HERE](https://huggingface.co/spaces/gmonsoon/SahabatAI-Lion-9B-TIES-v1)

## 🧩 Configuration

```yaml
models:
  - model: GoToCompany/gemma2-9b-cpt-sahabatai-v1-instruct
    parameters:
      weight: 1
      density: 1
  - model: GoToCompany/gemma2-9b-cpt-sahabatai-v1-instruct
    parameters:
      weight: 1
      density: 1
merge_method: ties
base_model: aisingapore/gemma2-9b-cpt-sea-lionv3-instruct
parameters:
  density: 1
  normalize: true
  int8_mask: true
dtype: bfloat16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "gmonsoon/SahabatAI-Lion-9B-TIES-v1"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```