Instructions to use CodeSoft/MetaDiffusion-150M-exp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CodeSoft/MetaDiffusion-150M-exp with Transformers:

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

pipe = pipeline("text-generation", model="CodeSoft/MetaDiffusion-150M-exp")

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("CodeSoft/MetaDiffusion-150M-exp", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CodeSoft/MetaDiffusion-150M-exp with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CodeSoft/MetaDiffusion-150M-exp"
# 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-150M-exp",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/CodeSoft/MetaDiffusion-150M-exp

SGLang

How to use CodeSoft/MetaDiffusion-150M-exp 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-150M-exp" \
    --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-150M-exp",
		"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-150M-exp" \
        --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-150M-exp",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use CodeSoft/MetaDiffusion-150M-exp with Docker Model Runner:
```
docker model run hf.co/CodeSoft/MetaDiffusion-150M-exp
```

CodeSoft commited on 2 days ago

Commit

0abb970

verified ·

1 Parent(s): 435e6e4

Add hfviewer architecture card

Browse files

Embed the hfviewer architecture visualization card in README.md.

Files changed (1) hide show

README.md +13 -4

README.md CHANGED Viewed

@@ -21,9 +21,9 @@ base_model:
 <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>
@@ -35,6 +35,16 @@ MetaDiffusion-150M-exp is a diffusion language model created by converting the S
 The model retains the original tokenizer while introducing diffusion-specific components, including timestep conditioning and a learned mask token.
 | Specification     | Value                                   |
 | ----------------- | --------------------------------------- |
 | Architecture      | `MetaDiffusionForCausalLM`              |
@@ -83,7 +93,6 @@ Training schedule:
 | Average Accuracy | 29.49% |
 | Average Normalized Accuracy | 29.61% |
 ## Running the Model
 This repository includes an `inference.py` script for sampling from the model.
@@ -135,4 +144,4 @@ This release is not instruction tuned and is not intended for production deploym
 ## 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.

 <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>
 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`              |
 | Average Accuracy | 29.49% |
 | Average Normalized Accuracy | 29.61% |
 ## Running the Model
 This repository includes an `inference.py` script for sampling from the model.
 ## 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.