Files
NovaCorp-Shadowncensored-1B…/README.md
ModelHub XC 11504aa2c9 初始化项目,由ModelHub XC社区提供模型
Model: Flexan/NovaCorp-Shadowncensored-1B-GGUF
Source: Original Platform
2026-06-30 10:07:16 +08:00

96 lines
4.4 KiB
Markdown

---
base_model: NovaCorp/Shadowncensored-1B
library_name: transformers
tags:
- mergekit
- merge
---
# GGUF Files for Shadowncensored-1B
These are the GGUF files for [NovaCorp/Shadowncensored-1B](https://huggingface.co/NovaCorp/Shadowncensored-1B).
## Downloads
| GGUF Link | Quantization | Description |
| ---- | ----- | ----------- |
| [Download](https://huggingface.co/Flexan/NovaCorp-Shadowncensored-1B-GGUF/resolve/main/Shadowncensored-1B.Q2_K.gguf) | Q2_K | Lowest quality |
| [Download](https://huggingface.co/Flexan/NovaCorp-Shadowncensored-1B-GGUF/resolve/main/Shadowncensored-1B.Q3_K_S.gguf) | Q3_K_S | |
| [Download](https://huggingface.co/Flexan/NovaCorp-Shadowncensored-1B-GGUF/resolve/main/Shadowncensored-1B.IQ3_S.gguf) | IQ3_S | Integer quant, preferable over Q3_K_S |
| [Download](https://huggingface.co/Flexan/NovaCorp-Shadowncensored-1B-GGUF/resolve/main/Shadowncensored-1B.IQ3_M.gguf) | IQ3_M | Integer quant |
| [Download](https://huggingface.co/Flexan/NovaCorp-Shadowncensored-1B-GGUF/resolve/main/Shadowncensored-1B.Q3_K_M.gguf) | Q3_K_M | |
| [Download](https://huggingface.co/Flexan/NovaCorp-Shadowncensored-1B-GGUF/resolve/main/Shadowncensored-1B.Q3_K_L.gguf) | Q3_K_L | |
| [Download](https://huggingface.co/Flexan/NovaCorp-Shadowncensored-1B-GGUF/resolve/main/Shadowncensored-1B.IQ4_XS.gguf) | IQ4_XS | Integer quant |
| [Download](https://huggingface.co/Flexan/NovaCorp-Shadowncensored-1B-GGUF/resolve/main/Shadowncensored-1B.Q4_K_S.gguf) | Q4_K_S | Fast with good performance |
| [Download](https://huggingface.co/Flexan/NovaCorp-Shadowncensored-1B-GGUF/resolve/main/Shadowncensored-1B.Q4_K_M.gguf) | Q4_K_M | **Recommended:** Perfect mix of speed and performance |
| [Download](https://huggingface.co/Flexan/NovaCorp-Shadowncensored-1B-GGUF/resolve/main/Shadowncensored-1B.Q5_K_S.gguf) | Q5_K_S | |
| [Download](https://huggingface.co/Flexan/NovaCorp-Shadowncensored-1B-GGUF/resolve/main/Shadowncensored-1B.Q5_K_M.gguf) | Q5_K_M | |
| [Download](https://huggingface.co/Flexan/NovaCorp-Shadowncensored-1B-GGUF/resolve/main/Shadowncensored-1B.Q6_K.gguf) | Q6_K | Very good quality |
| [Download](https://huggingface.co/Flexan/NovaCorp-Shadowncensored-1B-GGUF/resolve/main/Shadowncensored-1B.Q8_0.gguf) | Q8_0 | Best quality |
| [Download](https://huggingface.co/Flexan/NovaCorp-Shadowncensored-1B-GGUF/resolve/main/Shadowncensored-1B.f16.gguf) | f16 | Full precision, don't bother; use a quant |
## Note from Flexan
I provide GGUFs and quantizations of publicly available models that do not have a GGUF equivalent available yet,
usually for models **I deem interesting and wish to try out**.
If there are some quants missing that you'd like me to add, you may request one in the community tab.
If you want to request a public model to be converted, you can also request that in the community tab.
If you have questions regarding this model, please refer to [the original model repo](https://huggingface.co/NovaCorp/Shadowncensored-1B).
You can find more info about me and what I do [here](https://huggingface.co/Flexan/Flexan).
# Shadowncensored-1B
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [SLERP](https://en.wikipedia.org/wiki/Slerp) merge method.
### Models Merged
The following models were included in the merge:
* [lunahr/gemma-3-1b-it-abliterated](https://huggingface.co/lunahr/gemma-3-1b-it-abliterated)
* [Echo9Zulu/Shadows-Gemma-3-1B](https://huggingface.co/Echo9Zulu/Shadows-Gemma-3-1B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
# Umbrella Corporation Official Merge Protocol v3.2
# Author: Dr. Novaciano
# Objective: Test
# PROJECT: Shadowncensored-3.2-1B
models:
- model: lunahr/gemma-3-1b-it-abliterated # Experimental viral strain neural imprint
- model: Echo9Zulu/Shadows-Gemma-3-1B # Baseline cognitive template, "safe mode"
merge_method: slerp # Spherical Linear Interpolation to preserve extreme viral traits smoothly
base_model: lunahr/gemma-3-1b-it-abliterated # Anchor model for stable latent space
dtype: bfloat16 # Memory-efficient precision, minimal loss in viral feature fidelity
parameters:
t: 0.45
normalize: false
rescale: true
rescale_factor: 1.12
memory_efficient: true
low_cpu_mem_usage: true
layer_range:
- value: [4, 22]
tie_word_embeddings: true
tie_output_embeddings: true
```