README.md

---
base_model:
- yuvraj17/Llama-3-8B-spectrum-25
- ruggsea/Llama3-stanford-encyclopedia-philosophy-QA
- arcee-ai/Llama-3.1-SuperNova-Lite
tags:
- merge
- mergekit
- lazymergekit
- yuvraj17/Llama-3-8B-spectrum-25
- ruggsea/Llama3-stanford-encyclopedia-philosophy-QA
- arcee-ai/Llama-3.1-SuperNova-Lite
license: apache-2.0
language:
- en
pipeline_tag: text-classification
---

# Llama3-8B-SuperNova-Spectrum-dare_ties

Llama3-8B-SuperNova-Spectrum-dare_ties is a `DARE_TIES` merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [yuvraj17/Llama-3-8B-spectrum-25](https://huggingface.co/yuvraj17/Llama-3-8B-spectrum-25)
* [ruggsea/Llama3-stanford-encyclopedia-philosophy-QA](https://huggingface.co/ruggsea/Llama3-stanford-encyclopedia-philosophy-QA)
* [arcee-ai/Llama-3.1-SuperNova-Lite](https://huggingface.co/arcee-ai/Llama-3.1-SuperNova-Lite)

## DARE_TIES Merging

### TIES Merging

[TIES](https://arxiv.org/abs/2306.01708) Merging, introduced by Yadav et al. (2023), is a method for merging multiple specialized models into one general-purpose model. It solves two key challenges:
* **Redundancy Removal**: Identifies and eliminates overlapping or unnecessary information between models, making the final model more efficient.
* **Conflict Resolution**: Reconciles differences between models by creating a unified sign vector that represents the most dominant direction of change across all models.

### DARE Merging

Introduced by Yu et al. (2023), [DARE](https://arxiv.org/abs/2311.03099) uses an approach similar to TIES with two main differences:

* **Weight Pruning**: Randomly resets some fine-tuned weights to their original values, reducing model complexity.
* **Weight Scaling**: Adjusts the remaining weights by scaling and combining them with the base model's weights to maintain consistent performance.

Mergekit’s implementation of this method has two flavours: with the sign election step of TIES (`dare_ties`) or without (`dare_linear`).

For more information refer this [Merge Large Language Models with MergeKit by Maxime Labonne](https://towardsdatascience.com/merge-large-language-models-with-mergekit-2118fb392b54)

## 🧩 Configuration

```yaml
models:
  - model: NousResearch/Meta-Llama-3-8B
    # No parameters necessary for base model
  - model: yuvraj17/Llama-3-8B-spectrum-25
    parameters:
      density: 0.56
      weight: 0.12
  - model: ruggsea/Llama3-stanford-encyclopedia-philosophy-QA
    parameters:
      density: 0.56
      weight: 0.12
  - model: arcee-ai/Llama-3.1-SuperNova-Lite
    parameters:
      density: 0.58
      weight: 0.55
merge_method: dare_ties
base_model: NousResearch/Meta-Llama-3-8B
dtype: bfloat16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "yuvraj17/Llama3-8B-SuperNova-Spectrum-dare_ties"
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"])
```

## 🏆 Evaluation Scores
Coming soon


## Special thanks & Reference
- Maxime Labonne for their easy-to-use colab-notebook [Merging LLMs with MergeKit](https://github.com/mlabonne/llm-course/blob/main/Mergekit.ipynb) and [Blog](https://towardsdatascience.com/merge-large-language-models-with-mergekit-2118fb392b54)
- Authors of [Mergekit](https://github.com/arcee-ai/mergekit)