---
tags:
- merge
- mergekit
- lazymergekit
- CultriX/MergeCeption-7B-v3
base_model:
- CultriX/MergeCeption-7B-v3
license: apache-2.0
---

<img src="https://cdn-uploads.huggingface.co/production/uploads/6389d3c61e8755d777902366/-_AiKUEsY3x-N7oY52fdE.jpeg" style="border-radius:2%; width: 66%">


# pandafish-dt-7b

pandafish-dt-7b is a `dare_ties` merge of `Experiment26-7B` and `MergeCeption-7B-v3` using `LazyMergekit` by [mlabonne](https://huggingface.co/mlabonne)

## 💬 Try it

[Playground on Huggingface Space](https://huggingface.co/spaces/ichigoberry/pandafish-dt-7b)

## ⚡ Quantized models

- **GGUF**: [ichigoberry/pandafish-dt-7b-GGUF](https://huggingface.co/ichigoberry/pandafish-dt-7b-GGUF)
- **GGUF (w/ IQ)**: [mradermacher/pandafish-dt-7b-GGUF](https://huggingface.co/mradermacher/pandafish-dt-7b-GGUF)
- **MLX**: [4bit](https://huggingface.co/mlx-community/pandafish-dt-7b) [8bit](https://huggingface.co/mlx-community/pandafish-dt-7b-8bit)


## 🏆 Evals

Evals from the Nous Benchmark suite:

|                             Model                             |Average|AGIEval|GPT4All|TruthfulQA|Bigbench|
|---------------------------------------------------------------|------:|------:|---------:|-------:|------:|
|[AlphaMonarch-7B](https://huggingface.co/mlabonne/AlphaMonarch-7B) [📄](https://gist.github.com/mlabonne/1d33c86824b3a11d2308e36db1ba41c1) | **62.74** | 45.37 | 77.01 | 78.39 | **50.2** |
|[Monarch-7B](https://huggingface.co/mlabonne/Monarch-7B) [📄](https://gist.github.com/mlabonne/0b8d057c5ece41e0290580a108c7a093) | 62.68 | 45.48 | 77.07 | 78.04 | 50.14 |
|🐡 [**pandafish-dt-7b**](https://huggingface.co/ichigoberry/pandafish-dt-7b) [📄](https://gist.github.com/tosh/190e51bbd0048363e160f7031f8cb003)| 62.65| 45.24|  **77.19**|     **78.41**|   49.76|
|[MonarchPipe-7B-slerp](https://huggingface.co/ichigoberry/MonarchPipe-7B-slerp) [📄](https://gist.github.com/tosh/3d93f4e3d2c65935bf2f4f9a46791352)| 58.77|  **46.12**|  74.89|     66.59|   47.49|
|[NeuralHermes-2.5-Mistral-7B](https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B) [📄](https://gist.github.com/mlabonne/14687f1eb3425b166db511f31f8e66f6) | 53.51 | 43.67 | 73.24 | 55.37 | 41.76 |
|[Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) [📄](https://gist.github.com/mlabonne/05d358e17dffdf9eee7c2322380c9da6) | 54.81 | 38.5 | 71.64 | 66.82 | 42.29 |
|[OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) [📄](https://gist.github.com/mlabonne/88b21dd9698ffed75d6163ebdc2f6cc8) | 52.42 | 42.75 | 72.99 | 52.99 | 40.94 |
|[pandafish-7b](https://huggingface.co/ichigoberry/pandafish-7b) [📄](https://gist.github.com/tosh/dda6a21e568d17a410ca618265f64a28)| 51.99 | 40 | 74.23 | 53.22 | 40.51 |


## 🧩 Configuration

```yaml
models:
  - model: yam-peleg/Experiment26-7B
    # No parameters necessary for base model
  - model: CultriX/MergeCeption-7B-v3
    parameters:
      density: 0.53
      weight: 0.4
merge_method: dare_ties
base_model: yam-peleg/Experiment26-7B
parameters:
  int8_mask: true
dtype: bfloat16
```


## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "ichigoberry/pandafish-dt-7b"
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"])
```