---
base_model: Pinkstack/PARM-V1.5-QwQ-Qwen-2.5-o1-3B-VLLM
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
- gguf
- Reasoning
- o1
- qwq
license: apache-2.0
language:
- en
- zh
pipeline_tag: text-generation
---

![PARM-2.png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/9wMB_c4WmaJR91f-ybFJl.png)

We are proud to announce, our new high quality flagship model series - ***PARM2***, Very high quality reasoning, math and coding abilities for a small size, that **anyone** can run on their device for free.


 🧀 Which quant is right for you? 

- ***Q4:*** This model should be used on edge devices like high end phones or laptops due to its very compact size, quality is okay but fully usable. 
- ***Q8:*** This model should be used on most high end modern devices like rtx 3080, Responses are very high quality, but its slightly slower than Q4.
*other formats were not included as Q4,Q8 have the best performance, quality.*

This Parm v2 is based on Qwen 2.5 3B which has gotten many extra reasoning training parameters so it would have similar outputs to qwen QwQ / O.1 mini (only much, smaller.). We've trained it using the datasets [here](https://huggingface.co/collections/Pinkstackorg/pram-v2-67612d3c542b9121bf15891c)
if you benchmarked this model let me know

This is a pretty lite model which can be run on high end phones pretty quickly using the q4 quant.

# Passes "strawberry" test! (Q8 w/ msty & rtx 3080 10gb) ✅
![strawberry-test.png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/GQn5NqHn9GxdRyJtcIRAn.png)



To use this model, you must use a service which supports the GGUF file format.
Additionaly, this is the Prompt Template options:
efficient & accurate, answers stawberry text correctly 90% of the time.
```
{{ if .System }}<|system|>
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|user|>
{{ .Prompt }}<|im_end|>
{{ end }}<|assistant|>
{{ .Response }}<|im_end|>
```

Or if you are using an anti prompt: <|im_end|>

Highly recommended to use with a system prompt. eg;
You are a helpful assistant named Parm2 by Pinkstack. think step-by-step for complex stuff, use COT if neeed.


# Uploaded  model

- **Developed by:** Pinkstack
- **License:** apache-2.0
- **Finetuned from model :** Pinkstack/PARM-V1.5-QwQ-Qwen-2.5-o1-3B-VLLM

![Pinkstack.png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/2xMulpuSlZ3C1vpGgsAYi.png)

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