base_model, library_name, model_name, tags, license

base_model	library_name	model_name	tags	license
0xA50C1A1/Qwen3-4B-Instruct-2507-SOM-MPOA	transformers	Qwen3-4B-Nymphaea-RP	uncensored roleplay trl rp creative-writing	apache-2.0

Qwen3-4B-Nymphaea-RP

A fine-tune of Qwen3-4B-Instruct-2507 for roleplay and creative writing.

Suitable for mobile roleplay: tested on Nothing Phone 2 in Q4_K_M quantization (7-8 t/s)

Tip

The SillyTavern preset is available here. For custom presets, please use the ChatML instruct template.

Chat Example

Tested at Q8_0 quantization.

Training Notes

Trained on the latest iteration of my Darkmere dataset. This version features expanded genre variety, built upon a mix of manually curated synthetics and human-written stories.

Important

The base weights are abliterated via Heretic prior to fine-tuning, so this fine-tune is quite uncensored.

Training Specs

Method:

• Training Method: DoRA (Weight-Decomposed LoRA)
• Target Modules all-linear
• LoRA Rank: 32
• LoRA Alpha: 32
• LoRA Dropout: 0.05

Hyperparameters:

• Batch Size: 2 (Per-device)
• Gradient Accumulation: 2
• Epochs: 2
• Learning Rate: 1e-4
• Optimizer: adamw_torch_fused
• LR Scheduler: cosine
• Noise Level: neftune_noise_alpha=5

Special Thanks

This fine-tune wouldn't be possible without the incredible work of the community:

• p-e-w for developing Heretic - an essential tool for censorship removal.
• SicariusSicariiStuff for developing SLOP_Detector script.
• Qwen Team for their Qwen3 weights.
• AMD for their Instinct™ MI300X GPU.