---
tags:
- merge
- mergekit
- lazymergekit
- KoboldAI/Mistral-7B-Holodeck-1
- FPHam/Sydney_Pirate_Mistral_7b
base_model:
- KoboldAI/Mistral-7B-Holodeck-1
- FPHam/Sydney_Pirate_Mistral_7b
---

# HoloViolet-7B-test4

HoloViolet-7B-test4 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [KoboldAI/Mistral-7B-Holodeck-1](https://huggingface.co/KoboldAI/Mistral-7B-Holodeck-1)
* [FPHam/Sydney_Pirate_Mistral_7b](https://huggingface.co/FPHam/Sydney_Pirate_Mistral_7b)

## 🧩 Configuration

```yaml
merge_method: dare_ties
base_model: GreenNode/GreenNode-mini-7B-multilingual-v1olet
models:
  - model: GreenNode/GreenNode-mini-7B-multilingual-v1olet
  - model: KoboldAI/Mistral-7B-Holodeck-1
    parameters:
      weight: 0.42
  - model: FPHam/Sydney_Pirate_Mistral_7b
    parameters:
      weight: 0.21
dtype: bfloat16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "son-of-man/HoloViolet-7B-test4"
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"])
```