README.md

---
tags:
- merge
- mergekit
- lazymergekit
- saucam/Rudra-7b
- Telugu-LLM-Labs/Indic-gemma-7b-finetuned-sft-Navarasa-2.0
base_model:
- saucam/Rudra-7b
- Telugu-LLM-Labs/Indic-gemma-7b-finetuned-sft-Navarasa-2.0
---

# Navrasa-2.0-Rudra-7b-dare-ties

Navrasa-2.0-Rudra-7b-dare-ties is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [saucam/Rudra-7b](https://huggingface.co/saucam/Rudra-7b)
* [Telugu-LLM-Labs/Indic-gemma-7b-finetuned-sft-Navarasa-2.0](https://huggingface.co/Telugu-LLM-Labs/Indic-gemma-7b-finetuned-sft-Navarasa-2.0)

## 🧩 Configuration

```yaml
models:
  - model: saucam/Rudra-7b
    parameters:
      density: 0.5
      weight: 0.4
    # No parameters necessary for base model
  - model: Telugu-LLM-Labs/Indic-gemma-7b-finetuned-sft-Navarasa-2.0
    parameters:
      density: 0.5
      weight: 0.6
merge_method: dare_ties
base_model: Telugu-LLM-Labs/Indic-gemma-7b-finetuned-sft-Navarasa-2.0
parameters:
  int8_mask: true
dtype: bfloat16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "saucam/Navrasa-2.0-Rudra-7b-dare-ties"
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"])
```