---
language: en
license: apache-2.0
tags:
  - spelling-correction
  - dyslexia
  - text-correction
  - education
base_model: Qwen/Qwen3-1.7B
pipeline_tag: text-generation
---

# Dyslexic Writer - Qwen3-1.7B

Fine-tuned **Qwen/Qwen3-1.7B** for spelling and grammar correction, optimized for dyslexic writers.

## Performance

| Metric | Score |
|--------|-------|
| Exact Match Accuracy | 82.2% |
| Error Fix Rate | 75.9% |
| No-Error Preservation | 98.9% |
| F1 Score | 98.7% |

Trained on ~495K examples including word pairs, sentence corrections, and paragraph-level error injection from synthetic stories.

## Usage

### With Ollama (GGUF)

Download the Q4_K_M GGUF and create a Modelfile:

```
FROM ./dyslexic-writer-qwen3-1.7b-q4_k_m.gguf

PARAMETER temperature 0
PARAMETER num_predict 256

SYSTEM You are a spelling correction assistant.

TEMPLATE """<|im_start|>system
{{ .System }}<|im_end|>
<|im_start|>user
{{ .Prompt }}<|im_end|>
<|im_start|>assistant
<think>

</think>

"""
```

### With Transformers

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("jburnford/dyslexic-writer-qwen3-1.7b")
tokenizer = AutoTokenizer.from_pretrained("jburnford/dyslexic-writer-qwen3-1.7b")

messages = [
    {"role": "system", "content": "You are a spelling correction assistant."},
    {"role": "user", "content": "Fix any spelling mistakes in this text. If there are no mistakes, output the text unchanged.\n\nI went to teh store."},
]

prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=False)
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256, do_sample=False)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

## Model Variants

| Model | GGUF Q4_K_M | Exact Match | Best For |
|-------|-------------|-------------|----------|
| [Qwen3-0.6B](https://huggingface.co/jburnford/dyslexic-writer-qwen3-0.6b) | ~460 MB | 78.8% | Mobile/embedded |
| [Qwen3-1.7B](https://huggingface.co/jburnford/dyslexic-writer-qwen3-1.7b) | ~1.2 GB | 82.2% | Default |
| [Qwen3-4B](https://huggingface.co/jburnford/dyslexic-writer-qwen3-4b) | ~2.5 GB | 85.6% | Best quality |