---
tags:
- merge
- mergekit
- lazymergekit
- ecastera/eva-mistral-dolphin-7b-spanish
- ecastera/ecastera-eva-westlake-7b-spanish
- ecastera/eva-mistral-catmacaroni-7b-spanish
- Kukedlc/NeuralSirKrishna-Spanish-FT
base_model:
- ecastera/eva-mistral-dolphin-7b-spanish
- ecastera/ecastera-eva-westlake-7b-spanish
- ecastera/eva-mistral-catmacaroni-7b-spanish
- Kukedlc/NeuralSirKrishna-Spanish-FT
---

# NeuralSpanish-7b-v1

NeuralSpanish-7b-v1 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [ecastera/eva-mistral-dolphin-7b-spanish](https://huggingface.co/ecastera/eva-mistral-dolphin-7b-spanish)
* [ecastera/ecastera-eva-westlake-7b-spanish](https://huggingface.co/ecastera/ecastera-eva-westlake-7b-spanish)
* [ecastera/eva-mistral-catmacaroni-7b-spanish](https://huggingface.co/ecastera/eva-mistral-catmacaroni-7b-spanish)
* [Kukedlc/NeuralSirKrishna-Spanish-FT](https://huggingface.co/Kukedlc/NeuralSirKrishna-Spanish-FT)

## 🧩 Configuration

```yaml
models:
  - model: Kukedlc/NeuralSirKrishna-Spanish-FT
    # no parameters necessary for base model
  - model: ecastera/eva-mistral-dolphin-7b-spanish
    parameters:
      density: 0.65
      weight: 0.4
  - model: ecastera/ecastera-eva-westlake-7b-spanish
    parameters:
      density: 0.6
      weight: 0.35
  - model: ecastera/eva-mistral-catmacaroni-7b-spanish
    parameters:
      density: 0.6
      weight: 0.35
  - model: Kukedlc/NeuralSirKrishna-Spanish-FT
    parameters:
      density: 0.6
      weight: 0.35
merge_method: dare_ties
base_model: Kukedlc/NeuralSirKrishna-Spanish-FT
parameters:
  int8_mask: true
dtype: float16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Kukedlc/NeuralSpanish-7b-v1"
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"])
```