---
license: apache-2.0
datasets:
- HuggingFaceTB/smol-smoltalk
- HuggingFaceH4/no_robots
- nvidia/OpenMathInstruct-2
language:
- en
base_model:
- Qwen/Qwen3-0.6B
pipeline_tag: text-generation
library_name: transformers
tags:
- metadiffusion
- diffusion
- diffusion-lm
- ar-to-diffusion
---

# MetaDiffusion-600M-ChatBase

Experimental bidirectional masked-diffusion chat model converted from Qwen3-0.6B via AR-to-diffusion model surgery (28L x 1024W, ~0.82B params, untied head, bf16, 40K-token context (RoPE base 1e6), Apache-2.0). Intended as a base for further SFT, not a production chatbot.

## What this is

The AR checkpoint becomes the initialization (weights copied, timestep modules zero-init, the [MASK] and seven auxiliary "rainbow" padding rows are mean-initialized); diffusion behavior is learned throughout training. Trained using smol-smoltalk, no_robots, and OpenMathInstruct-2.

## Architecture
- Blocks: 28 transformer layers, hidden dim 1024, SwiGLU MLP with intermediate 3072, pre-norm RMSNorm (eps 1e-6), QK-norm on. Timestep conditioning is a sinusoidal MLP embedding (1024) feeding per-block adaLN-style scale+shift modulation.

- Attention: GQA with 16 query heads / 8 KV heads, head_dim 128. Bidirectional self-attention with no causal mask.

- Context: 40,960 tokens max (RoPE, base theta 1e6).

- Params: 0.82B total with untied embeddings: embed_tokens 151,677 x 1024 and a separate lm_head of the same size.

- Vocab / IO: 151,677 rows = Qwen3's 151,669 + [MASK] (id 151669) + 7 rainbow padding tokens (151670-151676); pad_token_id is <|endoftext|> (151643), eos is <|im_end|> (151645). bf16 weights, 371 tensors in model.safetensors.

## Use with Transformers

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

repo = "CodeSoft/MetaDiffusion-600M-ChatBase"

m = AutoModelForCausalLM.from_pretrained(
    repo,
    trust_remote_code=True,
    dtype=torch.bfloat16,
).to("cuda")

tok = AutoTokenizer.from_pretrained(
    repo,
    subfolder="tokenizer",
    trust_remote_code=True,
)

prompt = tok.apply_chat_template(
    [{"role": "user", "content": "hi"}],
    tokenize=False,
    add_generation_prompt=True,
)

inputs = tok(prompt, return_tensors="pt").to("cuda")

with torch.inference_mode():
    out = m.generate(
        **inputs,
        max_new_tokens=100,
    )

print(tok.decode(out[0], skip_special_tokens=True))

```

## Limitations

This model is an experimental research checkpoint intended for further fine-tuning and experimentation. It is not optimized for instruction-following, factuality, safety, or production deployment. Behavior may differ substantially from the original Qwen3-0.6B-Instruct model.

## License

Apache-2.0