---
tags:
- merge
- mergekit
- lazymergekit
- birgermoell/Flashback-Bellman
base_model:
- birgermoell/Flashback-Bellman
---

# BeagleCatMunin-Flashback-Bellman

BeagleCatMunin-Flashback-Bellman is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [birgermoell/Flashback-Bellman](https://huggingface.co/birgermoell/Flashback-Bellman)

## 🧩 Configuration

```yaml
  models:
    - model: timpal0l/BeagleCatMunin
      # No parameters necessary for base model
    - model: birgermoell/Flashback-Bellman
      parameters:
        density: 0.53
        weight: 0.6
  merge_method: dare_ties
  base_model: timpal0l/BeagleCatMunin
  parameters:
    int8_mask: true
  dtype: bfloat16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "birgermoell/BeagleCatMunin-Flashback-Bellman"
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"])
```