Quantization made by Richard Erkhov.

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

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

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


TinyQwex-4x620M-MoE - GGUF
- Model creator: https://huggingface.co/Isotonic/
- Original model: https://huggingface.co/Isotonic/TinyQwex-4x620M-MoE/


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [TinyQwex-4x620M-MoE.Q2_K.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_TinyQwex-4x620M-MoE-gguf/blob/main/TinyQwex-4x620M-MoE.Q2_K.gguf) | Q2_K | 0.49GB |
| [TinyQwex-4x620M-MoE.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_TinyQwex-4x620M-MoE-gguf/blob/main/TinyQwex-4x620M-MoE.IQ3_XS.gguf) | IQ3_XS | 0.54GB |
| [TinyQwex-4x620M-MoE.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_TinyQwex-4x620M-MoE-gguf/blob/main/TinyQwex-4x620M-MoE.IQ3_S.gguf) | IQ3_S | 0.56GB |
| [TinyQwex-4x620M-MoE.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_TinyQwex-4x620M-MoE-gguf/blob/main/TinyQwex-4x620M-MoE.Q3_K_S.gguf) | Q3_K_S | 0.56GB |
| [TinyQwex-4x620M-MoE.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_TinyQwex-4x620M-MoE-gguf/blob/main/TinyQwex-4x620M-MoE.IQ3_M.gguf) | IQ3_M | 0.57GB |
| [TinyQwex-4x620M-MoE.Q3_K.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_TinyQwex-4x620M-MoE-gguf/blob/main/TinyQwex-4x620M-MoE.Q3_K.gguf) | Q3_K | 0.6GB |
| [TinyQwex-4x620M-MoE.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_TinyQwex-4x620M-MoE-gguf/blob/main/TinyQwex-4x620M-MoE.Q3_K_M.gguf) | Q3_K_M | 0.6GB |
| [TinyQwex-4x620M-MoE.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_TinyQwex-4x620M-MoE-gguf/blob/main/TinyQwex-4x620M-MoE.Q3_K_L.gguf) | Q3_K_L | 0.64GB |
| [TinyQwex-4x620M-MoE.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_TinyQwex-4x620M-MoE-gguf/blob/main/TinyQwex-4x620M-MoE.IQ4_XS.gguf) | IQ4_XS | 0.67GB |
| [TinyQwex-4x620M-MoE.Q4_0.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_TinyQwex-4x620M-MoE-gguf/blob/main/TinyQwex-4x620M-MoE.Q4_0.gguf) | Q4_0 | 0.69GB |
| [TinyQwex-4x620M-MoE.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_TinyQwex-4x620M-MoE-gguf/blob/main/TinyQwex-4x620M-MoE.IQ4_NL.gguf) | IQ4_NL | 0.7GB |
| [TinyQwex-4x620M-MoE.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_TinyQwex-4x620M-MoE-gguf/blob/main/TinyQwex-4x620M-MoE.Q4_K_S.gguf) | Q4_K_S | 0.7GB |
| [TinyQwex-4x620M-MoE.Q4_K.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_TinyQwex-4x620M-MoE-gguf/blob/main/TinyQwex-4x620M-MoE.Q4_K.gguf) | Q4_K | 0.73GB |
| [TinyQwex-4x620M-MoE.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_TinyQwex-4x620M-MoE-gguf/blob/main/TinyQwex-4x620M-MoE.Q4_K_M.gguf) | Q4_K_M | 0.73GB |
| [TinyQwex-4x620M-MoE.Q4_1.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_TinyQwex-4x620M-MoE-gguf/blob/main/TinyQwex-4x620M-MoE.Q4_1.gguf) | Q4_1 | 0.76GB |
| [TinyQwex-4x620M-MoE.Q5_0.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_TinyQwex-4x620M-MoE-gguf/blob/main/TinyQwex-4x620M-MoE.Q5_0.gguf) | Q5_0 | 0.82GB |
| [TinyQwex-4x620M-MoE.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_TinyQwex-4x620M-MoE-gguf/blob/main/TinyQwex-4x620M-MoE.Q5_K_S.gguf) | Q5_K_S | 0.82GB |
| [TinyQwex-4x620M-MoE.Q5_K.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_TinyQwex-4x620M-MoE-gguf/blob/main/TinyQwex-4x620M-MoE.Q5_K.gguf) | Q5_K | 0.84GB |
| [TinyQwex-4x620M-MoE.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_TinyQwex-4x620M-MoE-gguf/blob/main/TinyQwex-4x620M-MoE.Q5_K_M.gguf) | Q5_K_M | 0.84GB |
| [TinyQwex-4x620M-MoE.Q5_1.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_TinyQwex-4x620M-MoE-gguf/blob/main/TinyQwex-4x620M-MoE.Q5_1.gguf) | Q5_1 | 0.88GB |
| [TinyQwex-4x620M-MoE.Q6_K.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_TinyQwex-4x620M-MoE-gguf/blob/main/TinyQwex-4x620M-MoE.Q6_K.gguf) | Q6_K | 0.96GB |
| [TinyQwex-4x620M-MoE.Q8_0.gguf](https://huggingface.co/RichardErkhov/Isotonic_-_TinyQwex-4x620M-MoE-gguf/blob/main/TinyQwex-4x620M-MoE.Q8_0.gguf) | Q8_0 | 1.24GB |




Original model description:
---
license: apache-2.0
tags:
- moe
- merge
- mergekit
- lazymergekit
- Qwen/Qwen1.5-0.5B
---

# TinyQwex-4x620M-MoE

TinyQwex-4x620M-MoE is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Qwen/Qwen1.5-0.5B](https://huggingface.co/Qwen/Qwen1.5-0.5B)
* [Qwen/Qwen1.5-0.5B](https://huggingface.co/Qwen/Qwen1.5-0.5B)
* [Qwen/Qwen1.5-0.5B](https://huggingface.co/Qwen/Qwen1.5-0.5B)
* [Qwen/Qwen1.5-0.5B](https://huggingface.co/Qwen/Qwen1.5-0.5B)

🌟 Buying me coffee is a direct way to show support for this project. 
<a href="https://www.buymeacoffee.com/isotonic"><img src="https://www.buymeacoffee.com/assets/img/guidelines/download-assets-sm-1.svg" alt=""></a>

## 💻 Usage

```python
!pip install -qU transformers bitsandbytes accelerate eniops

from transformers import AutoTokenizer
import transformers
import torch

model = "Isotonic/TinyQwex-4x620M-MoE"

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen1.5-0.5B")
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    model_kwargs={"torch_dtype": torch.bfloat16, "load_in_4bit": True},
)

messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
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"])
```

## 🧩 Configuration

```yamlbase_model: Qwen/Qwen1.5-0.5B
experts:
  - source_model: Qwen/Qwen1.5-0.5B
    positive_prompts:
    - "reasoning"

  - source_model: Qwen/Qwen1.5-0.5B
    positive_prompts:
    - "program"

  - source_model: Qwen/Qwen1.5-0.5B
    positive_prompts:
    - "storytelling"

  - source_model: Qwen/Qwen1.5-0.5B
    positive_prompts:
    - "Instruction following assistant"
```