Source model
Provided quantized models
ExLlamaV3: release v0.0.20
| Type | Size | CLI |
|---|---|---|
| H8-4.0BPW | 5.10 GB | Copy-paste the lines / Download the batch file |
| H8-6.0BPW | 6.84 GB | Copy-paste the lines / Download the batch file |
| H8-8.0BPW | 8.59 GB | Copy-paste the lines / Download the batch file |
Requirements: A python installation with huggingface-hub module to use CLI.
Licensing
License detected: apache-2.0
The license for the provided quantized models is inherited from the source model (which incorporates the license of its original base model). For definitive licensing information, please refer first to the page of the source or base models. File and page backups of the source model are provided below.
Backups
Date: 16.02.2026
Source page (click to expand)
⚠️ Warning: This model can produce narratives and RP that contain violent and graphic erotic content. Adjust your system prompt accordingly, and use Llama 3 chat template.
Raven 8B v1
A fully uncensored finetune of Llama-3.1-Nemotron-8B trained on a small dataset of Edgar Allan Poe corpus. Cooked for 5 epochs using PMPF.
{'loss': 0.1136, 'grad_norm': 1.0182174444198608, 'learning_rate': 1.685173482438018e-08, 'entropy': 0.18156841583549976, 'num_tokens': 99475.0, 'mean_token_accuracy': 0.9738506525754929, 'epoch': 5.0}
{'train_runtime': 590.173, 'train_samples_per_second': 0.847, 'train_steps_per_second': 0.212, 'train_loss': 1.036527609705925, 'epoch': 5.0}
