Source model
Avnas-7B-v1.1 by DarkArtsForge
Provided quantized models
ExLlamaV3: release v0.0.20
| Type | Size | CLI |
|---|---|---|
| H8-4.0BPW | 3.89 GB | Copy-paste the line / Download the batch file |
| H8-6.0BPW | 5.64 GB | Copy-paste the line / Download the batch file |
| H8-8.0BPW | 7.38 GB | Copy-paste the line / 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: 25.01.2026
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 Alpaca template.
Avnas 7B v1.1
v1.1 Training Steps: 200
Appears to be a bit more creative and detailed than v1, while just as uncensored. Going to 300 training steps caused language collapse (overcooked).
Note: Use Alpaca template to prevent errors. The dataset was specifically calibrated using Alpaca format due to issues with ChatML tokenizer.
\n### Instruction:\n \n### Response:\n