README.md

---
base_model:
- Guilherme34/Firefly
- SicariusSicariiStuff/Impish_LLAMA_3B
tags:
- merge
- mergekit
- lazymergekit
- Guilherme34/Firefly
- SicariusSicariiStuff/Impish_LLAMA_3B
library_name: transformers
---

# Firefly-V2

Firefly-V2 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Guilherme34/Firefly](https://huggingface.co/Guilherme34/Firefly)
* [SicariusSicariiStuff/Impish_LLAMA_3B](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B)

## 🧩 Configuration

```yaml
models:
  - model: Guilherme34/Firefly
    parameters:
      weight: 1.0

  - model: SicariusSicariiStuff/Impish_LLAMA_3B
    parameters:
      weight: 0.2

merge_method: task_arithmetic
base_model: Guilherme34/Firefly

dtype: bfloat16

parameters:
  normalize: true
  int8_mask: true
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Guilherme34/Firefly-V2"
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"])
```