README.md

---
tags:
- Kukedlc/NeuralMaths-Experiment-7b
- lemon-mint/gemma-ko-7b-instruct-v0.62
- Ppoyaa/StarMonarch-7B
- automerger/YamshadowExperiment28-7B
- ichigoberry/MonarchPipe-7B-slerp
- deepseek-ai/deepseek-coder-7b-instruct-v1.5
- Kukedlc/Neural-4-Maths-7b
base_model:
- Kukedlc/NeuralMaths-Experiment-7b
- lemon-mint/gemma-ko-7b-instruct-v0.62
- Ppoyaa/StarMonarch-7B
- automerger/YamshadowExperiment28-7B
- ichigoberry/MonarchPipe-7B-slerp
- deepseek-ai/deepseek-coder-7b-instruct-v1.5
- Kukedlc/Neural-4-Maths-7b
---

# DeepCode-7B-Aurora-v4

DeepCode-7B-Aurora-v4 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Kukedlc/NeuralMaths-Experiment-7b](https://huggingface.co/Kukedlc/NeuralMaths-Experiment-7b)
* [lemon-mint/gemma-ko-7b-instruct-v0.62](https://huggingface.co/lemon-mint/gemma-ko-7b-instruct-v0.62)
* [Ppoyaa/StarMonarch-7B](https://huggingface.co/Ppoyaa/StarMonarch-7B)
* [automerger/YamshadowExperiment28-7B](https://huggingface.co/automerger/YamshadowExperiment28-7B)
* [ichigoberry/MonarchPipe-7B-slerp](https://huggingface.co/ichigoberry/MonarchPipe-7B-slerp)
* [deepseek-ai/deepseek-coder-7b-instruct-v1.5](https://huggingface.co/deepseek-ai/deepseek-coder-7b-instruct-v1.5)
* [Kukedlc/Neural-4-Maths-7b](https://huggingface.co/Kukedlc/Neural-4-Maths-7b)

## 🧩 Configuration

```yaml
models:
  - model: Kukedlc/NeuralMaths-Experiment-7b
    parameters:
      weight: 1
  - model: lemon-mint/gemma-ko-7b-instruct-v0.62
    parameters:
      weight: 1
  - model: Ppoyaa/StarMonarch-7B
    parameters:
      weight: 1
  - model: automerger/YamshadowExperiment28-7B
    parameters:
      weight: 1
  - model: ichigoberry/MonarchPipe-7B-slerp
    parameters:
      weight: 1
  - model: deepseek-ai/deepseek-coder-7b-instruct-v1.5
    parameters:
      weight: 1
  - model: Kukedlc/Neural-4-Maths-7b
    parameters:
      weight: 1
merge_method: task_arithmetic
base_model: deepseek-ai/deepseek-math-7b-rl
parameters:
  normalize: true
  int8_mask: true
dtype: float16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "ALBADDAWI/DeepCode-7B-Aurora-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"])
```