Instructions to use diffutron/DiffutronLM-0.3B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use diffutron/DiffutronLM-0.3B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="diffutron/DiffutronLM-0.3B-Instruct")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("diffutron/DiffutronLM-0.3B-Instruct", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use diffutron/DiffutronLM-0.3B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "diffutron/DiffutronLM-0.3B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "diffutron/DiffutronLM-0.3B-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/diffutron/DiffutronLM-0.3B-Instruct

SGLang

How to use diffutron/DiffutronLM-0.3B-Instruct 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 "diffutron/DiffutronLM-0.3B-Instruct" \
    --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": "diffutron/DiffutronLM-0.3B-Instruct",
		"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 "diffutron/DiffutronLM-0.3B-Instruct" \
        --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": "diffutron/DiffutronLM-0.3B-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use diffutron/DiffutronLM-0.3B-Instruct with Docker Model Runner:
```
docker model run hf.co/diffutron/DiffutronLM-0.3B-Instruct
```

suayptalha commited on Mar 22

Commit

2fe4bf1

verified ·

1 Parent(s): 478d8b6

Update README.md

Browse files

Files changed (1) hide show

README.md +24 -0

README.md CHANGED Viewed

@@ -69,6 +69,30 @@ The model was evaluated on a representative subset of the **CETVEL Benchmark Sui
 Because Diffutron is a Masked Diffusion Language Model, it requires inference strategies distinct from standard causal generation. We recommend using the `dllm` library or custom generation loops tailored for discrete diffusion.
 ### Generation Parameters Used in Paper:
 * **Longer Context:** Steps: 128, Temp: 0.1, Block Length: 32, Repetition Penalty: 1.2
 * **Shorter Context:** Steps: 64, Remask: `low_conf`, Stochastic: `False`, CFG: 0.0

 Because Diffutron is a Masked Diffusion Language Model, it requires inference strategies distinct from standard causal generation. We recommend using the `dllm` library or custom generation loops tailored for discrete diffusion.
+### 1. Install the dllm Library:
+```bash
+git clone https://github.com/Diffutron/dllm.git
+cd dllm
+pip install -e .
+```
+### 2. Chat via Interaction Mode:
+```bash
+python -u examples/bert/chat.py \
+    --model_name_or_path "diffutron/DiffutronLM-0.3B-Instruct" \
+    --chat True \
+    --steps 64 \
+    --max_new_tokens 64 \
+    --temperature 0.1 \
+    --block_length 32 \
+    --repetition_penalty 1.2 \
+    --remasking "low_confidence" \
+    --stochastic_transfer False \
+    --cfg_scale 0.0
+```
+For other inference modes, see [dllm](https://github.com/Diffutron/dllm) library.
 ### Generation Parameters Used in Paper:
 * **Longer Context:** Steps: 128, Temp: 0.1, Block Length: 32, Repetition Penalty: 1.2
 * **Shorter Context:** Steps: 64, Remask: `low_conf`, Stochastic: `False`, CFG: 0.0