Model Stock: All we need is just a few fine-tuned models
Paper
• 2403.19522 • Published
• 13
Azure-Starlight-12B by Vortex5
ExLlamaV3: release v0.0.22
| Type | Size | CLI |
|---|---|---|
| H8-4.0BPW | 7.49 GB | Copy-paste the lines / Download the batch file |
| H8-6.0BPW | 10.22 GB | Copy-paste the lines / Download the batch file |
| H8-8.0BPW | 12.95 GB | Copy-paste the lines / Download the batch file |
Requirements: A python installation with huggingface-hub module to use CLI.
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.
Date: 27.02.2026
Azure-Starlight-12B was created by merging Astral-Noctra-12B, Starlit-Shadow-12B, Famino-12B-Model_Stock, and Crimson-Twilight-12B using the Model Stock method.
base_model: Vortex5/Astral-Noctra-12B
models:
- model: Vortex5/Starlit-Shadow-12B
- model: DreadPoor/Famino-12B-Model_Stock
- model: Vortex5/Crimson-Twilight-12B
- model: Vortex5/Astral-Noctra-12B
merge_method: model_stock
chat_template: auto
parameters:
normalize: true
dtype: float32
out_dtype: bfloat16
tokenizer:
source: Vortex5/Astral-Noctra-12B
Base model
Vortex5/Azure-Starlight-12B