---
license: apache-2.0
language:
- en
pipeline_tag: text-generation
library_name: transformers
tags:
- metadiffusion
- diffusion-language-model
- diffusion
- transformer
- language-model
- autoregressive-conversion
- experimental
- research
- 150m
- english
base_model:
- SupraLabs/Supra-1.5-50M-Base-exp
---

<div align="center">

<h1>MetaDiffusion-150M-exp</h1>

<p>
    This model is for research and evaluation purposes only. Do not use in production environments.
  </p>

</div>

## Architecture

MetaDiffusion-150M-exp is a diffusion language model created by converting the Supra-1.5-50M-Base-exp autoregressive model into a diffusion language model, then expanding it to approximately 150 million parameters through layer duplication before continued diffusion training.

The model retains the original tokenizer while introducing diffusion-specific components, including timestep conditioning and a learned mask token.

## Architecture graph

<a href="https://hfviewer.com/CodeSoft/MetaDiffusion-150M-exp?utm_source=huggingface&amp;utm_medium=embedded_model_card&amp;utm_campaign=CodeSoft_MetaDiffusion-150M-exp_card" target="_blank" rel="noopener">
  <img
    src="https://hfviewer.com/api/card.svg?source=CodeSoft%2FMetaDiffusion-150M-exp&amp;granularity=0"
    alt="Architecture graph for CodeSoft/MetaDiffusion-150M-exp. Open in hfviewer"
    width="100%"
  />
</a>

| Specification     | Value                                   |
| ----------------- | --------------------------------------- |
| Architecture      | `MetaDiffusionForCausalLM`              |
| Parameters        | ~169.5M                                 |
| Vocabulary Size   | 32,001 (32,000 + MASK token)            |
| Hidden Size       | 768                                     |
| Intermediate Size | 2,112                                   |
| Layers            | 16                                      |
| Attention Heads   | 12                                      |
| KV Heads          | 6                                       |
| Head Dimension    | 64                                      |
| Context Length    | 5,120 tokens                            |
| Tokenizer         | Original Supra byte-level BPE tokenizer |
| Activation        | SiLU                                    |
| RoPE θ            | 10,000                                  |
| Model Type        | Diffusion Language Model                |

## Data

Training was performed in two stages:

1. Autoregressive-to-diffusion conversion using the Supra-1.5-50M-Base-exp checkpoint
2. Model expansion from approximately 50M to 150M parameters via layer duplication, followed by continued diffusion pretraining.

Training schedule:

| Stage                        | Dataset     |   Steps |
| ---------------------------- | ----------- | ------: |
| Initial diffusion training   | FineWeb-EDU | 100,000 |
| Continued diffusion training | The Pile    |  50,000 |

## Benchmarks

**Evaluation:** lm-evaluation-harness (0-shot)

| Benchmark | Samples | Accuracy | Normalized Accuracy |
|---|---:|---:|---:|
| ARC-Easy | 2,376 | 38.30% | 35.40% |
| ARC-Challenge | 1,172 | 18.86% | 21.84% |
| ArithMark-3 | 1,000 | 31.30% | 31.60% |

### Average Scores

| Metric | Score |
|---|---:|
| Average Accuracy | 29.49% |
| Average Normalized Accuracy | 29.61% |

## Running the Model

This repository includes an `inference.py` script for sampling from the model.

Example:

```bash
python inference.py \
  --model-path ./model.safetensors \
  --prompt "The cat sat on the" \
  --num-steps 256
```

### Command Line Arguments

| Flag                   | Description                                           | Default                            |
| ---------------------- | ----------------------------------------------------- | ---------------------------------- |
| `--model-path`         | Path to a local checkpoint or Hugging Face repository | Required                           |
| `--prompt`             | Input prompt                                          | `"The cat sat on the"`             |
| `--seq-len`            | Number of generated tokens                            | `256`                              |
| `--num-steps`          | Number of diffusion denoising steps                   | `256`                              |
| `--temperature`        | Sampling temperature                                  | `0.6`                              |
| `--repetition-penalty` | Repetition penalty                                    | `1.5`                              |
| `--device`             | `cuda` or `cpu`                                       | `cuda`                             |
| `--watch`              | Display intermediate denoising progress               | Disabled                           |
| `--watch-every`        | Display every N denoising iterations                  | `4`                                |
| `--base-model`         | Tokenizer source                                      | `SupraLabs/Supra-1.5-50M-Base-exp` |

## Generation Defaults

| Setting            | Value |
| ------------------ | ----: |
| Denoising Steps    |   512 |
| Temperature        |   0.6 |
| Repetition Penalty |   1.5 |
| Re-mask Ratio      |   0.1 |
| Max New Tokens     |   512 |

## Intended Use

MetaDiffusion-150M-exp is intended for:

* Research on diffusion language models.
* Experiments involving autoregressive-to-diffusion conversion.
* Benchmarking novel diffusion language model architectures.
* Further finetuning and experimentation.

This release is not instruction tuned and is not intended for production deployments.

## Acknowledgements

MetaDiffusion is derived from the Supra-1.5-50M-Base-exp model. Credit goes to the Supra authors for the original autoregressive checkpoint that served as the initialization for this work. MetaDiffusion is released under the Apache-2.0 license in accordance with the licensing terms of the original Supra checkpoint.