QuantFactory Banner

QuantFactory/SmallThinker-3B-Preview-abliterated-GGUF

This is quantized version of huihui-ai/SmallThinker-3B-Preview-abliterated created using llama.cpp

Original Model Card

huihui-ai/SmallThinker-3B-Preview-abliterated

This is an uncensored version of PowerInfer/SmallThinker-3B-Preview created with abliteration (see remove-refusals-with-transformers to know more about it).
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.

Use with ollama

You can use huihui_ai/smallthinker-abliterated directly

ollama run huihui_ai/smallthinker-abliterated
Downloads last month
643
GGUF
Model size
3.4B params
Architecture
qwen2

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference API
Unable to determine this model's library. Check the docs .

Model tree for QuantFactory/SmallThinker-3B-Preview-abliterated-GGUF

Base model

Qwen/Qwen2.5-3B
Quantized
(17)
this model