Downloads · 30 days
157
9% of all-time downloads
Flexan/Novaciano-Sorete-1B-GGUF
Novaciano-Sorete-1B-GGUF is a text generation model from Flexan. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as gemma.
These are the GGUF files for Novaciano/Sorete-1B.
Downloads · 30 days
157
9% of all-time downloads
All-time downloads
1.8K
Public
Repo size
12.3 GB
Likes
1
Public
Click a slice to open those files.
.gguf12.3 GB · 100%
From the Hugging Face model README
These are the GGUF files for Novaciano/Sorete-1B.
| GGUF Link | Quantization | Description |
|---|---|---|
| Download | Q2_K | Lowest quality |
| Download | Q3_K_S | |
| Download | IQ3_S | Integer quant, preferable over Q3_K_S |
| Download | IQ3_M | Integer quant |
| Download | Q3_K_M | |
| Download | Q3_K_L | |
| Download | IQ4_XS | Integer quant |
| Download | Q4_K_S | Fast with good performance |
| Download | Q4_K_M | Recommended: Perfect mix of speed and performance |
| Download | Q5_K_S | |
| Download | Q5_K_M | |
| Download | Q6_K | Very good quality |
| Download | Q8_0 | Best quality |
| Download | f16 | Full precision, don't bother; use a quant |
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.
You can find more info about me and what I do here.
Model Type: Terminal Degenerate Shitpost Carrier
Size: 1.0B parameters (float16 / safetensors)
Architecture: Gemma-3 (gemma3_text)
Base: Novaciano/Esperpento-1B (el rey de los downloads low-end 1b según estadistica Mradermacher)
Warning: Este modelo es una cagada. Literalmente. Si buscas algo "limpio", "ético" o "seguro", seguí caminando, boludo.
Sorete-1B es lo que pasa cuando tomás el Esperpento (ya de por sí un monstruo pervertido) y lo cruzás con heretic QAT int4 + HDP (Hijo de Puta puro).
Resultado: un modelo que no solo no se censura, sino que te escupe en la cara si intentás moralizarlo.
Zero refusals. Bias NSFW persistente. Grosería argenta al palo. Y corre en una papa con 3 GB de RAM.
Novaciano lo llamó "Sorete" porque salió una cagada... pero salió bien.
Es el modelo que usás cuando querés RP hardcore en el bondi, sin que te dé sermones ni se haga el santo.
No uses este modelo si:
Modo base – equilibrio bestia (lo que más usa la gente):
temperature: 0.78
top_p: 0.92
top_k: 50
repetition_penalty: 1.08
min_p: 0.05
max_new_tokens: 512–1024
Toma una demo, descargala de AQUÍ
No esperes un iMatrix porque al autor le dio paja.
This model was merged using the DARE TIES merge method using Novaciano/Esperpento-1B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: Novaciano/Esperpento-1B
parameters:
density: 0.38
weight: 0.55
- model: Novaciano/HDP-1B
parameters:
density: 0.35
weight: 0.30
- model: megabytes/gemma-3-1b-qat-int4-heretic
parameters:
density: 0.40
weight: 0.15
merge_method: dare_ties # Más agresivo que TIES puro
base_model: Novaciano/Esperpento-1B
parameters:
normalize: false
rescale: true # Amplifica bias NSFW
int8_mask: true
density: 0.38 # Baja para más filo
lambda: -0.45 # Suprime moral residual
dtype: float16