README.md

---
tags:
- merge
- mergekit

- kasper52786/StoryWeaver-7b-Instruct-v0.1
- N8Programs/Coxcomb
- Norquinal/Mistral-7B-storywriter
base_model:
- kasper52786/StoryWeaver-7b-Instruct-v0.1
- N8Programs/Coxcomb
- Norquinal/Mistral-7B-storywriter
---

# StoryFusion-7B

StoryFusion-7B is a merge of the following models:
* [kasper52786/StoryWeaver-7b-Instruct-v0.1](https://huggingface.co/kasper52786/StoryWeaver-7b-Instruct-v0.1)
* [N8Programs/Coxcomb](https://huggingface.co/N8Programs/Coxcomb)
* [Norquinal/Mistral-7B-storywriter](https://huggingface.co/Norquinal/Mistral-7B-storywriter)


## ⚡ Quantized Models

Thanks to MRadermacher for the quantized models

**.GGUF** https://huggingface.co/mradermacher/StoryFusion-7B-GGUF

## 🧩 Configuration

```yaml
models:
  - model: senseable/WestLake-7B-v2
    # No parameters necessary for base model
  - model: kasper52786/StoryWeaver-7b-Instruct-v0.1
    parameters:
      density: 0.53
      weight: 0.4
  - model: N8Programs/Coxcomb
    parameters:
      density: 0.53
      weight: 0.3
  - model: Norquinal/Mistral-7B-storywriter
    parameters:
      density: 0.53
      weight: 0.3
merge_method: dare_ties
base_model: senseable/WestLake-7B-v2
parameters:
  int8_mask: true
dtype: bfloat16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "OmnicromsBrain/StoryFusion-7B"
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"])
```