---
tags:
- merge
- mergekit
- lazymergekit
- Kukedlc/NeuralKrishna-7B-v3
- Kukedlc/NeuralMarioMonarch-7B-slerp
- liminerity/M7-7b
base_model:
- Kukedlc/NeuralKrishna-7B-v3
- Kukedlc/NeuralMarioMonarch-7B-slerp
- liminerity/M7-7b
license: apache-2.0
---

# NeuralKrishna-7B-v4

![NeuralKrishna-7B-v3](https://raw.githubusercontent.com/kukedlc87/imagenes/main/DALL%C2%B7E%202024-02-17%2005.09.10%20-%20Imagine%20a%20large%20language%20model%20represented%20as%20an%20abstract%2C%20ethereal%20entity%2C%20made%20of%20swirling%20codes%20and%20data%20streams%2C%20lying%20on%20a%20classic%20psychoanalysis.webp)

NeuralKrishna-7B-v4 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Kukedlc/NeuralKrishna-7B-v3](https://huggingface.co/Kukedlc/NeuralKrishna-7B-v3)
* [Kukedlc/NeuralMarioMonarch-7B-slerp](https://huggingface.co/Kukedlc/NeuralMarioMonarch-7B-slerp)
* [liminerity/M7-7b](https://huggingface.co/liminerity/M7-7b)

## 🧩 Configuration

```yaml
models:
  - model: Kukedlc/NeuralKrishna-7B-v3
    # no parameters necessary for base model
  - model: Kukedlc/NeuralKrishna-7B-v3
    parameters:
      density: 0.65
      weight: 0.36
  - model: Kukedlc/NeuralMarioMonarch-7B-slerp
    parameters:
      density: 0.6
      weight: 0.34
  - model: liminerity/M7-7b
    parameters:
      density: 0.4
      weight: 0.3
merge_method: dare_ties
base_model: Kukedlc/NeuralKrishna-7B-v3
parameters:
  int8_mask: true
dtype: bfloat16
random_seed: 0
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Kukedlc/NeuralKrishna-7B-v4"
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"])
```