README.md

Quantization made by Richard Erkhov.

[Github](https://github.com/RichardErkhov)

[Discord](https://discord.gg/pvy7H8DZMG)

[Request more models](https://github.com/RichardErkhov/quant_request)


pandafish-7b - GGUF
- Model creator: https://huggingface.co/ichigoberry/
- Original model: https://huggingface.co/ichigoberry/pandafish-7b/


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [pandafish-7b.Q2_K.gguf](https://huggingface.co/RichardErkhov/ichigoberry_-_pandafish-7b-gguf/blob/main/pandafish-7b.Q2_K.gguf) | Q2_K | 2.53GB |
| [pandafish-7b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/ichigoberry_-_pandafish-7b-gguf/blob/main/pandafish-7b.IQ3_XS.gguf) | IQ3_XS | 2.81GB |
| [pandafish-7b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/ichigoberry_-_pandafish-7b-gguf/blob/main/pandafish-7b.IQ3_S.gguf) | IQ3_S | 2.96GB |
| [pandafish-7b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/ichigoberry_-_pandafish-7b-gguf/blob/main/pandafish-7b.Q3_K_S.gguf) | Q3_K_S | 2.95GB |
| [pandafish-7b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/ichigoberry_-_pandafish-7b-gguf/blob/main/pandafish-7b.IQ3_M.gguf) | IQ3_M | 3.06GB |
| [pandafish-7b.Q3_K.gguf](https://huggingface.co/RichardErkhov/ichigoberry_-_pandafish-7b-gguf/blob/main/pandafish-7b.Q3_K.gguf) | Q3_K | 3.28GB |
| [pandafish-7b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/ichigoberry_-_pandafish-7b-gguf/blob/main/pandafish-7b.Q3_K_M.gguf) | Q3_K_M | 3.28GB |
| [pandafish-7b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/ichigoberry_-_pandafish-7b-gguf/blob/main/pandafish-7b.Q3_K_L.gguf) | Q3_K_L | 3.56GB |
| [pandafish-7b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/ichigoberry_-_pandafish-7b-gguf/blob/main/pandafish-7b.IQ4_XS.gguf) | IQ4_XS | 3.67GB |
| [pandafish-7b.Q4_0.gguf](https://huggingface.co/RichardErkhov/ichigoberry_-_pandafish-7b-gguf/blob/main/pandafish-7b.Q4_0.gguf) | Q4_0 | 3.83GB |
| [pandafish-7b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/ichigoberry_-_pandafish-7b-gguf/blob/main/pandafish-7b.IQ4_NL.gguf) | IQ4_NL | 3.87GB |
| [pandafish-7b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/ichigoberry_-_pandafish-7b-gguf/blob/main/pandafish-7b.Q4_K_S.gguf) | Q4_K_S | 3.86GB |
| [pandafish-7b.Q4_K.gguf](https://huggingface.co/RichardErkhov/ichigoberry_-_pandafish-7b-gguf/blob/main/pandafish-7b.Q4_K.gguf) | Q4_K | 4.07GB |
| [pandafish-7b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/ichigoberry_-_pandafish-7b-gguf/blob/main/pandafish-7b.Q4_K_M.gguf) | Q4_K_M | 4.07GB |
| [pandafish-7b.Q4_1.gguf](https://huggingface.co/RichardErkhov/ichigoberry_-_pandafish-7b-gguf/blob/main/pandafish-7b.Q4_1.gguf) | Q4_1 | 4.24GB |
| [pandafish-7b.Q5_0.gguf](https://huggingface.co/RichardErkhov/ichigoberry_-_pandafish-7b-gguf/blob/main/pandafish-7b.Q5_0.gguf) | Q5_0 | 4.65GB |
| [pandafish-7b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/ichigoberry_-_pandafish-7b-gguf/blob/main/pandafish-7b.Q5_K_S.gguf) | Q5_K_S | 4.65GB |
| [pandafish-7b.Q5_K.gguf](https://huggingface.co/RichardErkhov/ichigoberry_-_pandafish-7b-gguf/blob/main/pandafish-7b.Q5_K.gguf) | Q5_K | 4.78GB |
| [pandafish-7b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/ichigoberry_-_pandafish-7b-gguf/blob/main/pandafish-7b.Q5_K_M.gguf) | Q5_K_M | 4.78GB |
| [pandafish-7b.Q5_1.gguf](https://huggingface.co/RichardErkhov/ichigoberry_-_pandafish-7b-gguf/blob/main/pandafish-7b.Q5_1.gguf) | Q5_1 | 5.07GB |
| [pandafish-7b.Q6_K.gguf](https://huggingface.co/RichardErkhov/ichigoberry_-_pandafish-7b-gguf/blob/main/pandafish-7b.Q6_K.gguf) | Q6_K | 5.53GB |
| [pandafish-7b.Q8_0.gguf](https://huggingface.co/RichardErkhov/ichigoberry_-_pandafish-7b-gguf/blob/main/pandafish-7b.Q8_0.gguf) | Q8_0 | 7.17GB |




Original model description:
---
tags:
- merge
- mergekit
- lazymergekit
license: apache-2.0
---


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

# pandafish-7b

pandafish-7b is an instruct model based on a [Model Stock](https://arxiv.org/abs/2403.19522) merge of the following models (via [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing)):

## 🧩 Configuration

```yaml
models:
  - model: mistralai/Mistral-7B-v0.1
  - model: mistralai/Mistral-7B-Instruct-v0.2
  - model: CultriX/NeuralTrix-bf16
  - model: OpenPipe/mistral-ft-optimized-1227
merge_method: model_stock
base_model: mistralai/Mistral-7B-v0.1
dtype: bfloat16
```

## 🏆 Evals

|                             Model                             |Average|AGIEval|GPT4All|TruthfulQA|Bigbench|
|---------------------------------------------------------------|------:|------:|---------:|-------:|------:|
|[pandafish-7b](https://huggingface.co/ichigoberry/pandafish-7b) [📄](https://gist.github.com/tosh/dda6a21e568d17a410ca618265f64a28)| 51.99 | **40** | **74.23** | 53.22 | 40.51 |
|[mistralai/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** |


## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "ichigoberry/pandafish-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"])
```