This model is a specialized fine-tune of Qwen-3 4b, optimized specifically for the Polyglot Air desktop application workflow. This version was trained on a dataset approximately 4 times larger than its predecessor, significantly expanding its range of commands and improving the accuracy of its responses.
It has been trained to strictly adhere to suffix-based commands, ensuring instant, clean, and direct responses without conversational filler, hallucinations, or "Here is the translation" preambles.
🎯 Purpose
The default chat models often struggle with context switching when presented with short strings followed by a command (e.g., text::en). They might explain the translation or chat with the user.
This model is fine-tuned to treat the ::suffix as a strict instruction code.
- Input:
O arquivo não pode ser salvo porque o disco está cheio::en - Output:
The file cannot be saved because the disk is full
⚡ Suffix Command Table
Use these suffixes at the end of your selected text to trigger specific transformations.
Translation
| Suffix | Action | Example Input | Model Output |
|---|---|---|---|
::en | Translate to English | Bom dia::en | Good morning |
::pt | Translate to Portuguese (Portugal) | Good morning::pt | Bom dia |
::ptbr | Translate to Portuguese (Brazil) | The bus is coming::ptbr | O ônibus está vindo |
::es | Translate to Spanish | Hello friend::es | Hola amigo |
::zh | Translate to Chinese (Simplified) | Hello::zh | 你好 |
Tone & Style Adjustment
| Suffix | Action | Example Input | Model Output |
|---|---|---|---|
::fix | Fix spelling and grammar | i goes to skool yesterday::fix | I went to school yesterday |
::formal | Rewrite in a professional/formal tone | Hey, send me that file asap::formal | Could you please send me that file as soon as possible? |
::casual | Rewrite in a casual tone | I acknowledge receipt of your message::casual | Got your message, thanks! |
::informal | Rewrite in a slang/informal tone | That is very interesting::informal | That's pretty cool |
::polite | Make polite | I need the report now.::polite | Could you please provide the report when you have a moment? |
::technical | Make technical | The computer is broken.::technical | The CPU is experiencing a critical hardware failure. |
::creative | Make creative | The sun set.::creative | The sun painted the sky in hues of fire and gold. |
::business | Make business-oriented | We should sell more.::business | We must optimize our sales funnel to increase revenue. |
::news | Rewrite in a news style | A car crashed on the main street.::news | A vehicular collision occurred on Main Street earlier today. |
::social | Rewrite in a social media style | I'm launching a new product.::social | 🔥 BIG NEWS! So excited to launch our new product! #launch #new |
Content & Structure Manipulation
| Suffix | Action | Example Input | Model Output |
|---|---|---|---|
::summarize | Summarize the text | [Long Text]::summarize | [Concise Summary] |
::expand | Expand / add details | The project was a success.::expand | The project was a resounding success, exceeding all initial expectations. |
::elaborate | Elaborate / add details | She was happy.::elaborate | A wide smile spread across her face, and her eyes sparkled with joy. |
::simplify | Simplify the text | The confluence of factors precipitated this.::simplify | Many things caused this to happen. |
::concise | Make concise | Due to the fact that it was raining, we left.::concise | We left because it was raining. |
::toQuestion | Transform into a question | The report is due tomorrow.::toQuestion | Is the report due tomorrow? |
::toStatement | Transform into a statement | Should we start the project?::toStatement | We should start the project. |
🚀 How to use with Polyglot Air
- Download this model (or the GGUF version if available).
- Add it to your Ollama library.
- Open Polyglot Air.
- Go to Settings > Model and select this model.
- Enjoy seamless, instruction-following transformations.
Uploaded finetuned model
- Developed by: CalmState
- License: apache-2.0
- Finetuned from model : unsloth/Qwen3-4B-Instruct-2507
This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.