---
license: mit
datasets:
- HuggingFaceTB/smollm-corpus
language:
- en
pipeline_tag: text-generation
library_name: transformers
tags:
- moe
- causal-lm
- mistral
- tiny-moe
---

# TinyMoE-200M-2x16

**TinyMoE-200M-2x16** is a compact, highly efficient Sparse Mixture of Experts (MoE) language model built upon the Mixtral/Mistral architecture. Designed for research, edge applications, and resource-constrained environments, this model leverages an expert-routing mechanism to balance a larger total parameter capacity with ultra-low computational overhead during inference.

## Model Details

* **Architecture:** Sparse Mixture of Experts (MoE)
* **Total Parameters:** ~200m total parameters
* **Active Parameters per Token:** ~50M active parameters
* **Expert Configuration:** 16 total local experts, 2 active experts routed per token (`num_experts_per_tok": 2`)
* **Context Length:** 1024 tokens
* **Base Architecture:** Mixtral / Mistral For Causal LM
* **License:** MIT

## Training Data

This model was trained on`FineWeb-Edu-Dedup` 60% and `Cosmopedia-v2` 40%.

![image](https://cdn-uploads.huggingface.co/production/uploads/6615494716917dfdc645c44e/35iLfOIZI-tKMP2TUJ40E.png)
![image](https://cdn-uploads.huggingface.co/production/uploads/6615494716917dfdc645c44e/IyrW-dzolURCavH-AD5a2.png)
![image](https://cdn-uploads.huggingface.co/production/uploads/6615494716917dfdc645c44e/eNsiJy4VXV3zFh2v-qAoF.png)
![image](https://cdn-uploads.huggingface.co/production/uploads/6615494716917dfdc645c44e/37VEpxpu99tJiTAqPJtcT.png)
![image](https://cdn-uploads.huggingface.co/production/uploads/6615494716917dfdc645c44e/5Z3Xh9xtFnACgO4-qtamg.png)

## Quick Start

You can load and experiment with this model using the Hugging Face `transformers` library:

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "FlameF0X/TinyMoE-200m-2x16"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

input_text = "Wikipedia is a free"
inputs = tokenizer(input_text, return_tensors="pt")

outputs = model.generate(**inputs, max_new_tokens=50)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```