Instructions to use CodeSoft/MetaDiffusion-600M-ChatBase with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CodeSoft/MetaDiffusion-600M-ChatBase with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="CodeSoft/MetaDiffusion-600M-ChatBase", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("CodeSoft/MetaDiffusion-600M-ChatBase", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CodeSoft/MetaDiffusion-600M-ChatBase with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CodeSoft/MetaDiffusion-600M-ChatBase"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CodeSoft/MetaDiffusion-600M-ChatBase",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/CodeSoft/MetaDiffusion-600M-ChatBase

SGLang

How to use CodeSoft/MetaDiffusion-600M-ChatBase with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "CodeSoft/MetaDiffusion-600M-ChatBase" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CodeSoft/MetaDiffusion-600M-ChatBase",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "CodeSoft/MetaDiffusion-600M-ChatBase" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CodeSoft/MetaDiffusion-600M-ChatBase",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use CodeSoft/MetaDiffusion-600M-ChatBase with Docker Model Runner:
```
docker model run hf.co/CodeSoft/MetaDiffusion-600M-ChatBase
```

MetaDiffusion-600M-ChatBase / README.md

CodeSoft

Update README.md

f3e0e57 verified 6 days ago

2.71 kB

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

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