---
library_name: mlx
base_model: mlx-community/gemma-4-12b-it-bf16
tags:
- lora
- mlx
- mlx-lm
- gemma
- gemma-4
- assembly
- reverse-engineering
- systems
license: apache-2.0
---

# Gemma 4 12B — ASM & Systems Specialist LoRA (Expert 4)

Specialist LoRA adapter fine-tuned on top of `mlx-community/gemma-4-12b-it-bf16` for low-level assembly analysis, binary reverse engineering, decompilation reasoning, and systems programming.

Designed as **Expert 4** within multi-specialist MoE fusion architectures or for standalone low-level code auditing on Apple Silicon via Apple MLX (`mlx_lm`).

---

## Model Specifications

| Parameter | Specification |
| :--- | :--- |
| **Base Model** | `mlx-community/gemma-4-12b-it-bf16` |
| **Adapter Architecture** | LoRA (Low-Rank Adaptation) |
| **Target Layers** | 48 Transformer Layers (`q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj`) |
| **LoRA Rank (`r`)** | `16` |
| **LoRA Alpha (`α`)** | `32` |
| **LoRA Scale** | `10.0` |
| **Dropout** | `0.05` |
| **Max Sequence Length** | `8192` tokens |
| **Training Framework** | `mlx-lm` on Apple Silicon Metal |

---

## Training Domain & Technical Capabilities

Fine-tuned specifically for low-level software engineering and binary inspection tasks:

1. **Assembly & Disassembly Analysis:**
   * Reading, explaining, and translating x86_64, ARM64, and RISC-V assembly routines.
   * Calling convention tracing, stack frame layout analysis, and register allocation diagnostics.
2. **Decompilation & Binary Engineering:**
   * Reconstructing equivalent high-level C/C++ source code from stripped machine instructions.
   * Identifying compiler idioms, loop unrolling, and inline optimization patterns.
3. **Systems & Operating Systems Internals:**
   * Low-level POSIX/Kernel APIs, memory allocation internals, virtual memory paging, and hardware/software interfacing.

---

## Usage with Apple MLX (`mlx-lm`)

### Installation
```bash
pip install mlx mlx-lm
```

### Python Inference
```python
from mlx_lm import load, generate

model_path = "mlx-community/gemma-4-12b-it-bf16"
adapter_path = "True2456/Gemma-4-12B-ASM-Systems-LoRA"

model, tokenizer = load(
    model_path,
    adapter_path=adapter_path
)

prompt = tokenizer.apply_chat_template([
    {"role": "user", "content": "Analyze the following x86_64 prologue and explain its stack frame layout and arguments:\npush rbp\nmov rbp, rsp\nsub rsp, 0x20\nmov [rbp-0x8], rdi\nmov [rbp-0x10], rsi"}
], tokenize=False, add_generation_prompt=True)

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

---

## Training Details

* **Batch Size / Accumulation:** Batch size 4, trained with MLX gradient checkpointing on Apple Silicon M-Series hardware.
* **Intended Role:** Specialist adapter for systems programming, disassembly inspection, and reverse engineering assistance.