quantflex's picture
Update README.md
a0efcae verified
|
raw
history blame
706 Bytes
---
license: other
license_name: qwen-research
license_link: LICENSE
language:
- en
pipeline_tag: text-generation
base_model: huihui-ai/SmallThinker-3B-Preview-abliterated
tags:
- chat
---
GGUF Quants for: [huihui-ai/SmallThinker-3B-Preview-abliterated](https://huggingface.co/huihui-ai/SmallThinker-3B-Preview-abliterated)
Model by: [huihui-ai](https://huggingface.co/huihui-ai) (thank you!)
Quants by: [quantflex](https://huggingface.co/quantflex)
Run with [llama.cpp](https://github.com/ggerganov/llama.cpp):
```./llama-cli -m SmallThinker-3B-Preview-abliterated-Q5_K_M.gguf -p 'You are a helpful assistant.' --temp 0.7 --top-p 0.8 --top-k 20 --repeat-penalty 1.1 -cnv --chat-template chatml```