Files
ModelHub XC 7d64580e9b 初始化项目,由ModelHub XC社区提供模型
Model: 0xA50C1A1/Llama-3.3-8B-Nymphaea-RP
Source: Original Platform
2026-04-27 05:37:04 +08:00

60 lines
2.1 KiB
Markdown

---
base_model: 0xA50C1A1/Llama-3.3-8B-Instruct-128K-SOM-MPOA
library_name: transformers
model_name: Llama-3.3-8B-Nymphaea-RP
tags:
- uncensored
- roleplay
- trl
- rp
- creative-writing
license: apache-2.0
---
# Llama-3.3-8B-Nymphaea-RP
A fine-tune of Llama 3.3 8B Instruct for roleplay and creative writing.
I've trained this mostly for merging with Llama 3.1/3.3 8B fine-tunes.
> [!Tip]
> The SillyTavern preset is available [here](https://huggingface.co/0xA50C1A1/Llama-3.3-8B-Nymphaea-RP/blob/main/ST-Preset.json).
> For custom presets, please use the **Llama 3** instruct template.
## 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](https://github.com/p-e-w/heretic) prior to fine-tuning, so this fine-tune is quite uncensored.
<details>
<summary>Training Specs</summary><p>
**Method:**
* **Training Method:** DoRA (Weight-Decomposed LoRA)
* **Target Modules** `all-linear`
* **LoRA Rank:** 64
* **LoRA Alpha:** 64
* **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`
</p></details>
## Special Thanks
This fine-tune wouldn't be possible without the incredible work of the community:
* **[p-e-w](https://huggingface.co/p-e-w)** for developing **[Heretic](https://github.com/p-e-w/heretic)** - an essential tool for censorship removal.
* **[SicariusSicariiStuff](https://huggingface.co/SicariusSicariiStuff)** for developing **[SLOP_Detector](https://github.com/SicariusSicariiStuff/SLOP_Detector)** script.
* **[allura-forge](https://huggingface.co/allura-forge)** and **[shb777](https://huggingface.co/shb777)** for providing access to the **Llama 3.3 8B** weights.
* **[AMD](https://oneclickamd.ai/)** for their Instinct™ MI300X GPU.