---
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
pipeline_tag: text-generation
---

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

⚠️ it may think it's name is Claude due to the training data, we are sorry for this issue but is shouldn't effect the quality of the responses. 

 🧀 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 noticeably slower than q4

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)

This is a pretty heavy to run model if you want on device ai's for phones I'd recommend using the 0.5B version of this model (coming soon)


To use this model, you must use a service which supports the GGUF file format.
Additionaly, this is the Prompt Template: it uses the qwen2 template.
```
{{ if .System }}<|system|>
{{ .System }}<|end|>
{{ end }}{{ if .Prompt }}<|user|>
{{ .Prompt }}<|end|>
{{ end }}<|assistant|>
{{ .Response }}<|end|>
```

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

Highly recommended to use with a system prompt. 


# Uploaded  model

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

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