README.md

---
tags:
- merge
- mergekit
- lazymergekit
- automerger/YamShadow-7B
- Kukedlc/Neural4gsm8k
- Kukedlc/NeuralSirKrishna-7b
- mlabonne/NeuBeagle-7B
- Kukedlc/Ramakrishna-7b
- Kukedlc/NeuralGanesha-7b
base_model:
- automerger/YamShadow-7B
- Kukedlc/Neural4gsm8k
- Kukedlc/NeuralSirKrishna-7b
- mlabonne/NeuBeagle-7B
- Kukedlc/Ramakrishna-7b
- Kukedlc/NeuralGanesha-7b
license: apache-2.0
---

# Ramakrishna-7b-v3

Ramakrishna-7b-v3 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [automerger/YamShadow-7B](https://huggingface.co/automerger/YamShadow-7B)
* [Kukedlc/Neural4gsm8k](https://huggingface.co/Kukedlc/Neural4gsm8k)
* [Kukedlc/NeuralSirKrishna-7b](https://huggingface.co/Kukedlc/NeuralSirKrishna-7b)
* [mlabonne/NeuBeagle-7B](https://huggingface.co/mlabonne/NeuBeagle-7B)
* [Kukedlc/Ramakrishna-7b](https://huggingface.co/Kukedlc/Ramakrishna-7b)
* [Kukedlc/NeuralGanesha-7b](https://huggingface.co/Kukedlc/NeuralGanesha-7b)

## 🧩 Configuration

```yaml
models:
  - model: automerger/YamShadow-7B
    # No parameters necessary for base model
  - model: automerger/YamShadow-7B
    parameters:
      density: 0.6
      weight: 0.2
  - model: Kukedlc/Neural4gsm8k
    parameters:
      density: 0.3
      weight: 0.1
  - model: Kukedlc/NeuralSirKrishna-7b
    parameters:
      density: 0.6
      weight: 0.2
  - model: mlabonne/NeuBeagle-7B
    parameters:
      density: 0.5
      weight: 0.15
  - model: Kukedlc/Ramakrishna-7b
    parameters:
      density: 0.6
      weight: 0.25
  - model: Kukedlc/NeuralGanesha-7b
    parameters:
      density: 0.6
      weight: 0.1
merge_method: dare_ties
base_model: automerger/YamShadow-7B
parameters:
  int8_mask: true
dtype: bfloat16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Kukedlc/Ramakrishna-7b-v3"
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"])
```