README.md

---
tags:
- merge
- mergekit
- lazymergekit
- Equall/Saul-7B-Instruct-v1
- timpal0l/Mistral-7B-v0.1-flashback-v2-instruct
base_model:
- Equall/Saul-7B-Instruct-v1
- timpal0l/Mistral-7B-v0.1-flashback-v2-instruct
---

# BellmanSaul-flashback-dareties

BellmanSaul-flashback-dareties is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Equall/Saul-7B-Instruct-v1](https://huggingface.co/Equall/Saul-7B-Instruct-v1)
* [timpal0l/Mistral-7B-v0.1-flashback-v2-instruct](https://huggingface.co/timpal0l/Mistral-7B-v0.1-flashback-v2-instruct)

## 🧩 Configuration

```yaml
models:
  - model: neph1/bellman-7b-mistral-instruct-v0.2
    # No parameters necessary for base model
  - model: Equall/Saul-7B-Instruct-v1
    parameters:
      density: 0.53
      weight: 0.7
  - model: timpal0l/Mistral-7B-v0.1-flashback-v2-instruct
    parameters:
      density: 0.53
      weight: 0.3
merge_method: dare_ties
base_model: neph1/bellman-7b-mistral-instruct-v0.2
parameters:
  int8_mask: true
dtype: bfloat16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Knobi3/BellmanSaul-flashback-dareties"
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"])
```