---
license: mit
datasets:
- Tesslate/Rust_Dataset
language:
- en
base_model:
- unsloth/phi-4-reasoning
pipeline_tag: text-generation
library_name: transformers
tags:
- Rust
- code
- text-generation-inference
- lora
- reasoning
- quantization
---
# 🧠 Rust-Master-thinking

This repository contains a fine-tuned version of
[**unsloth/phi-4-reasoning**](https://huggingface.co/unsloth/phi-4-reasoning), trained with **LoRA** on the
[**Tesslate/Rust_Dataset**](https://huggingface.co/datasets/Tesslate/Rust_Dataset).
The goal of this project is to enhance the model's reasoning,
explanation, and step-by-step thinking abilities specifically for
**Rust-related tasks**.

## 🚀 Model Purpose

This model was fine-tuned to:

-   Improve **Rust coding explanations**
-   Generate **high-quality reasoning traces**
-   Provide **step-by-step problem solving**
-   Give **detailed and structured answers**

The training format follows:

    <|user|>
    {prompt}
    <|assistant|>
    <think>
    {reasoning}
    </think>
    {response}

## 🔧 How to Use

### Install dependencies (if not installed):
```bash
pip install transformers bitsandbytes
```
### Load model normally:

``` python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "SkyAsl/Rust-Master-thinking"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, dtype=torch.bfloat16, device_map="auto")
model.eval()

prompt = "Explain why Rust ownership prevents data races."

input_text = (
    f"<|user|>\n{prompt}\n"
    f"<|assistant|>\n<think>\n"
)

inputs = tokenizer(input_text, return_tensors="pt").to(model.device)

with torch.no_grad():
    output = model.generate(
        **inputs,
        max_new_tokens=3000,
        temperature=0.7,
        top_p=0.9,
        do_sample=True,
        repetition_penalty=1.2,
    )

print(tokenizer.decode(output[0], skip_special_tokens=False))

```

## 🧩 Base Model

**unsloth/phi-4-reasoning**

-   14B parameter reasoning-optimized model
-   Uses internal `<think>` reasoning
-   Strong on step-by-step chain-of-thought tasks

## 🛠 Fine-Tuning Details

  | Setting | Value |
  |----------------|-----------------------------------------|
  | Method | LoRA (PEFT) |
  | Rank (r) | 16 |
  | Alpha | 32 |
  | Dropout | 0.05 |
  | Target Modules | q/k/v/o proj, mlp (up/down/gate) |
  | Max Length | 512 |
  | Precision | 4-bit QLoRA |
  | Batch Size | 16 |
  | Grad Accum | 8 |
  | LR | 2e-4 |
  | Scheduler | cosine |
  | Epochs | 1 |

## 🤖 Evaluation
| Epoch | Training Loss | Validation Loss |
|-------|----------------|------------------|
|   1   |    2.251500    |     2.191743     |

## 📚 Dataset

**Tesslate/Rust_Dataset**

Includes:

-   Rust prompts
-   Step-by-step reasoning
-   Final answers

This dataset improves the model's ability to produce structured and
accurate explanations for Rust programming tasks.