---
tags:
- text-generation-inference
- transformers
- unsloth
- gguf
- reasoning
- Qwen2
- Qwen
license: apache-2.0
language:
- en
pipeline_tag: text-generation
---

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

[PRAM V2](https://huggingface.co/collections/Pinkstackorg/pram-v2-67612d3c542b9121bf15891c)

# 🧀 Which quant is right for you? 

- ***Q4:*** This model should be used for super low end devices like older phones or older laptops due to its very compact size, quality is okay but fully usable. 
- ***Q6:*** This model should be used on most modern devices, good quality and very quick responses. 
- ***Q8:*** This model should be used on most modern devices Responses are very high quality, but its a little slower than q6
- ***BF16:*** This Lossless model should only be used if maximum quality is needed; it doesn't perform well speed wise, but text results are high quality.

## Things you should be aware of when using PARM models (Pinkstack Accuracy Reasoning Models) 🧀

This PARM is based on Qwen 2.5 0.5B which has gotten extra reasoning training parameters so it would have similar outputs to qwen QwQ (only much, smaller.), We trained with [this](https://huggingface.co/datasets/gghfez/QwQ-LongCoT-130K-cleaned) dataset.
it is designed to run on any device, from your phone to high-end PC. that is why we've included a BF16 quant.


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 .Suffix }}<|fim_prefix|>{{ .Prompt }}<|fim_suffix|>{{ .Suffix }}<|fim_middle|>
{{- else if .Messages }}
{{- if or .System .Tools }}<|im_start|>system
{{- if .System }}
{{ .System }}
{{- end }}
{{- if .Tools }}
# Tools
You may call one or more functions to assist with the user query.
You are provided with function signatures within <tools></tools> XML tags:
<tools>
{{- range .Tools }}
{"type": "function", "function": {{ .Function }}}
{{- end }}
</tools>
For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
<tool_call>
{"name": <function-name>, "arguments": <args-json-object>}
</tool_call>
{{- end }}<|im_end|>
{{ end }}
{{- range $i, $_ := .Messages }}
{{- $last := eq (len (slice $.Messages $i)) 1 -}}
{{- if eq .Role "user" }}<|im_start|>user
{{ .Content }}<|im_end|>
{{- else if eq .Role "assistant" }}<|im_start|>assistant
{{ if .Content }}{{ .Content }}
{{- else if .ToolCalls }}<tool_call>
{{ range .ToolCalls }}{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}}
{{ end }}</tool_call>
{{- end }}{{ if not $last }}<|im_end|>
{{ end }}
{{- else if eq .Role "tool" }}<|im_start|>user
<tool_response>
{{ .Content }}
</tool_response><|im_end|>
{{ end }}
{{- if and (ne .Role "assistant") $last }}<|im_start|>assistant
{{ end }}
{{- end }}
{{- else }}
{{- if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{- end }}{{ if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>
{{ end }}<|im_start|>assistant
{{ end }}{{ .Response }}{{ if .Response }}<|im_end|>{{ end }}
```

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

Highly recommended to use with a system prompt. 

# Extra information
- **Developed by:** Pinkstack
- **License:** apache-2.0
- **Finetuned from model :** unsloth/qwen2.5-0.5b-instruct-bnb-4bit

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

Used this model? Don't forget to leave a like :)

[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)