README.md

---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- mistralai/Mistral-7B-v0.1
- HuggingFaceH4/zephyr-7b-alpha
- cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
---

# Fulcrum_Aura1

Fulcrum_Aura1 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
* [HuggingFaceH4/zephyr-7b-alpha](https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha)
* [cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser](https://huggingface.co/cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser)

## 🧩 Configuration

```yaml
slices:
  - sources:
      - model: mistralai/Mistral-7B-v0.1
        layer_range: [0, 32]
      - model: HuggingFaceH4/zephyr-7b-alpha
        layer_range: [0, 32]
        parameters:
          density: 0.53
          weight: 0.4
      - model: cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
        layer_range: [0, 32]
        parameters:
          density: 0.53
          weight: 0.4
merge_method: dare_linear
base_model: mistralai/Mistral-7B-v0.1
parameters:
  int8_mask: true
dtype: bfloat16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Spanicin/Fulcrum_Aura1"
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"])
```