README.md

---
base_model:
- bigcode/starcoder2-3b
- TechxGenus/starcoder2-3b-instruct
tags:
- merge
- mergekit
- lazymergekit
- bigcode/starcoder2-3b
- TechxGenus/starcoder2-3b-instruct
---

# tinyllama-merged

tinyllama-merged is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [bigcode/starcoder2-3b](https://huggingface.co/bigcode/starcoder2-3b)
* [TechxGenus/starcoder2-3b-instruct](https://huggingface.co/TechxGenus/starcoder2-3b-instruct)

## 🧩 Configuration

```yaml
models:
  - model : bigcode/starcoder2-3b
    parameters:
      density: 0.5 # density gradient
      weight: 1
  - model: TechxGenus/starcoder2-3b-instruct
    parameters:
      density: 0.5
      weight: 1 # weight gradient
tokenizer_source: union
merge_method: ties
base_model: bigcode/starcoder2-3b
parameters:
  normalize: true
  int8_mask: true
dtype: float16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "choprahetarth/tinyllama-merged"
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"])
```