README.md

---
language:
- en
- zh
- es
- ja
- ru
- ko
license: apache-2.0
tags:
- mlx
- qwen3
- trace-inverter
- trace-inversion
- reasoning
- synthetic-data
- 8-bit
pipeline_tag: text-generation
library_name: mlx
base_model:
- Jackrong/Trace-Inverter-4B
---

# Trace-Inverter-4B-MLX-8bit

This is an 8-bit MLX conversion of [Jackrong/Trace-Inverter-4B](https://huggingface.co/Jackrong/Trace-Inverter-4B), a Qwen3-based trace inversion model.

The model is intended to reconstruct a detailed synthetic reasoning trace from:

```text
Problem + Model final answer + Reasoning Bubbles
```

The original weights are BF16. This MLX version was converted with `mlx-lm` using 8-bit affine quantization with group size 64.

## Use With MLX

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("omercelik/Trace-Inverter-4B-MLX-8bit")

messages = [
    {
        "role": "system",
        "content": (
            "You are a trace inversion model. Given a problem, a final answer, "
            "and several compressed reasoning bubbles, reconstruct a detailed "
            "reasoning trace that could plausibly lead to the final answer."
        ),
    },
    {
        "role": "user",
        "content": """Problem:
If a pizza needs 10 cups of water, 16 cups of flour, and salt equal to half the flour amount, what is the combined total?

Model final answer:
34 cups.

Reasoning Bubbles:
I need to calculate the salt first because it is defined as half of the flour amount. Then I should add water, flour, and salt together to get the combined total.

Reconstruct the full reasoning trace.""",
    },
]

prompt = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_dict=False,
)

response = generate(
    model,
    tokenizer,
    prompt=prompt,
    max_tokens=512,
    verbose=True,
)
```

## Notes

The source checkpoint stores PEFT-style LoRA-wrapped tensors inside the safetensors files. For MLX compatibility, the LoRA tensors were merged into plain model weights before conversion. The inferred LoRA scale used for the merge was `1.0`.

The source model card notes that outputs may occasionally include stray tool tags such as `<tool_call>`. Post-processing is recommended when generating datasets.

Generated traces are synthetic reasoning traces. They should not be treated as recovered hidden chain-of-thought from any closed model.