Instructions to use s-sahoo/uno-qwen3-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use s-sahoo/uno-qwen3-8B with Transformers:

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

pipe = pipeline("text-generation", model="s-sahoo/uno-qwen3-8B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("s-sahoo/uno-qwen3-8B", trust_remote_code=True, device_map="auto")

PEFT
How to use s-sahoo/uno-qwen3-8B with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use s-sahoo/uno-qwen3-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "s-sahoo/uno-qwen3-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "s-sahoo/uno-qwen3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/s-sahoo/uno-qwen3-8B

SGLang

How to use s-sahoo/uno-qwen3-8B 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 "s-sahoo/uno-qwen3-8B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "s-sahoo/uno-qwen3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "s-sahoo/uno-qwen3-8B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "s-sahoo/uno-qwen3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use s-sahoo/uno-qwen3-8B with Docker Model Runner:
```
docker model run hf.co/s-sahoo/uno-qwen3-8B
```

s-sahoo

nielsr HF Staff commited on 4 days ago

Commit

016d976

1 Parent(s): 8819e09

Add paper and project page links to model card (#2)

Browse files

- Add paper and project page links to model card (24f3d8252d3dc4383e75ae0aaa0162c8de1319e3)

Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

Files changed (1) hide show

README.md +14 -11

README.md CHANGED Viewed

@@ -1,21 +1,24 @@
 ---
-license: apache-2.0
-library_name: transformers
 base_model: IFM/uno-qwen3-8b-base
 pipeline_tag: text-generation
 tags:
-  - diffusion-language-model
-  - qwen3
-  - sdar
-  - custom_code
-  - peft
-  - lora
-  - speculative-decoding
-  - uno
 ---
 <h1 align="center"><strong>Uno Qwen3-8B</strong></h1>
 ![Diffusion-augmented LLM training and evaluation overview](./results_overview.png)
 This repository is a self-contained inference bundle for Uno-Qwen3-8B. The
@@ -112,4 +115,4 @@ UNO_BUNDLE_REVISION=<pinned-commit-sha> \
 The repository contains custom model code. Conventional Transformers loading
 of the base checkpoint requires `trust_remote_code=True`. Official Uno
 generation additionally requires conditional adapter routing and lossless
-verification implemented by the Uno runtime.

 ---
 base_model: IFM/uno-qwen3-8b-base
+library_name: transformers
+license: apache-2.0
 pipeline_tag: text-generation
 tags:
+- diffusion-language-model
+- qwen3
+- sdar
+- custom_code
+- peft
+- lora
+- speculative-decoding
+- uno
 ---
 <h1 align="center"><strong>Uno Qwen3-8B</strong></h1>
+**Paper:** [Unlocking Lossless Speedups in LLMs via Discrete Diffusion](https://huggingface.co/papers/2609.04010)
+**Project page:** [https://s-sahoo.github.io/uno/](https://s-sahoo.github.io/uno/)
 ![Diffusion-augmented LLM training and evaluation overview](./results_overview.png)
 This repository is a self-contained inference bundle for Uno-Qwen3-8B. The
 The repository contains custom model code. Conventional Transformers loading
 of the base checkpoint requires `trust_remote_code=True`. Official Uno
 generation additionally requires conditional adapter routing and lossless
+verification implemented by the Uno runtime.