---
base_model: Pinkstack/PARM-2-Smollm2-1.7B-Lcot-PyTorch
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- gguf
- o1
- qwq
license: apache-2.0
language:
- en
pipeline_tag: text-generation
---

![tinyparmv2.png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/EFmHghzKy4HpQDgwDG68A.png)

Currently underground testing! 
This tiny parm is based on: Smollm2 by HuggingFaceH4. 

It is designed to be highly conversational but with better results than the original model, q8 can be run locally on mobile devices.
We've trained it very similarly to the bigger Parm V2 models but with a bigger focus on code generation improvements. 

More information soon. This readme will be updated.

- **Developed by:** Pinkstack
- **License:** apache-2.0
- **Finetuned from model :** Pinkstack/PARM-2-Smollm2-1.7B-Lcot-PyTorch

This model was trained with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.