21 lines
1023 B
Markdown
21 lines
1023 B
Markdown
---
|
|
license: apache-2.0
|
|
language:
|
|
- en
|
|
base_model:
|
|
- Goekdeniz-Guelmez/Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v2
|
|
pipeline_tag: text-generation
|
|
tags:
|
|
- roleplay
|
|
---
|
|
# 💘 Cupid-Qwen3-4B-v0.2
|
|
|
|
**Cupid-Qwen3-4B-v0.2** is a LoRA fine-tune of **Goekdeniz-Guelmez/Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v2** specifically for non-reasoning, uncensored Roleplay (RP).
|
|
|
|
This version is a small update featuring a cleaned and expanded dataset over v0.1.
|
|
|
|
Nowadays, RP models are either massive or are heavily reasoning-focused, which I found just slow down the experience. The objective of Cupid-Qwen3-4B-v0.2 is to bring back the feeling of the LLama 2 and 3 RP fine-tunes.
|
|
|
|
**Available Formats:** This repository includes only the **16-bit PyTorch/Safetensors** version, for the **GGUF quantizations** visit [this repo](https://huggingface.co/ToreroDev/Cupid-Qwen3-4B-v0.2-GGUF).
|
|
|
|
**Note:** This model is based on Qwen3 architecture. Ensure you have the necessary dependencies for Qwen models if you run into issues. |