---
license: mit
language:
- en
tags:
- text-generation-inference
pipeline_tag: text-generation
---

![if-your-ai-girlfriend-is-not-a-locally-running-fine-tuned-v0-04wo67pdnuvf1](https://cdn-uploads.huggingface.co/production/uploads/64b7618e2f5a966b972e9978/8x-Ef3kxYJMfhwZ1CPHvp.png)

## GPT-Fem
An 81-million parameter LLM using GPT-2 encodings.
Trained using 16GB of text relating to and made by women, along with 1GB of multilingual text. (5.2 billion tokens)

This model should be fine-tuned before use.

![Screenshot from 2026-01-18 22-57-13](https://cdn-uploads.huggingface.co/production/uploads/64b7618e2f5a966b972e9978/50XOSomGKO0FQRtPEOjUO.png)

## Languages:
English,
Turkish,
Swedish,
Serbian,
Portugese,
Norwegian,
Welsh,
Thai,
Polish,
French,
Finnish,
Dutch,
Arabic,
Korean,
Japanese,
Danish,
Croatian,
Spanish,
Russian,
Chinese


## Technical Information
|                                 |     |
|---------------------------------|----:|
|Layers                           |10|
|Heads                            |10|
|Embeddings                       |640|
|Context Window                   |4096 tokens|
|Tokenizer                        |GPT-2 BPE|


## Training Information
|                                 |     |
|---------------------------------|----:|
|Training Loss                    |3.0|
|Validation Loss                  |2.99|
|Device                           |Google Colab A100|
|Training Time                    |5 Hours|