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
```

Uno Qwen3-8B

This repository is a self-contained inference bundle for Uno-Qwen3-8B. The frozen verifier/base checkpoint is stored at the repository root, and the rank-128 gated LoRA adapter used for noisy draft rows is stored under adapter/.

Uno applies the adapter selectively during draft-noise forwards. Seed, prefill, verification, and autoregressive rows use the frozen base weights. Loading the adapter as an ordinary always-on PEFT adapter does not reproduce Uno decoding.

Repository layout

s-sahoo/uno-qwen3-8B
|-- config.json
|-- model-*.safetensors
|-- model.safetensors.index.json
|-- modeling_sdar.py
|-- tokenizer files
`-- adapter/
    |-- adapter_config.json
    `-- adapter_model.safetensors

Evaluation protocol

The reproducible entry points are the Qwen benchmark wrappers in ifm-ai/uno. Unless an experiment explicitly overrides a setting, the release wrappers use the following protocol:

Setting	Value
Runtime	Uno with conditional gated-LoRA routing
Sampler	Linear diffusion
Diffusion block size	16
Temperature	1.0
Top-p	0.95
Top-k	50
Samples per problem	1
Noise mode	`random_uniform`
Served context length	32,768 tokens
Maximum batched tokens	32,768
Maximum sequences per replica	64
Data / tensor parallel size	8 / 1
Attention backend	FlashAttention 2

Math tasks use the instruction Please reason step by step and put your final answer in \boxed{}.. Benchmarks that request it in the release configuration use reasoning_effort=high through the chat template.

Benchmark	Problems	Scoring
GSM8K	1,319	Mathematical answer equivalence
MATH-500	500	Mathematical answer equivalence
AIME 2024	30	Mathematical answer equivalence
AIME 2025	30	Mathematical answer equivalence
AIME 2026	30	Mathematical answer equivalence
HumanEval	164	Code execution
MBPP	500	Code execution
LiveCodeBench v6 shard	175	Public and private test execution
GPQA Main	448	Multiple-choice answer matching
GPQA Diamond	198	Multiple-choice answer matching
MMLU-Pro	12,032	Multiple-choice answer matching
IFEval	541	Strict and loose instruction following
AA-LCR	100	External judge; data and judge must be supplied separately

Generation artifacts are written to generations.jsonl. generation_summary.json records all resolved settings, aggregate output TPS, and TPF as accepted tokens divided by decoder sequence-forwards. Accuracy and grader details are written to grades.jsonl and scores.json when the selected benchmark has a local grader.

from huggingface_hub import snapshot_download

snapshot = snapshot_download(
    "s-sahoo/uno-qwen3-8B",
    revision="<pinned-commit-sha>",
)
print("Base:", snapshot)
print("Adapter:", f"{snapshot}/adapter")

With the Uno repository:

UNO_BUNDLE_REPO=s-sahoo/uno-qwen3-8B \
UNO_BUNDLE_REVISION=<pinned-commit-sha> \
  bash scripts/qwen/run_gsm8k_eval.sh

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.

Downloads last month: 127

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for s-sahoo/uno-qwen3-8B

Base model

IFM/uno-qwen3-8b

Adapter

(1)

this model

Collection including s-sahoo/uno-qwen3-8B

uno

Collection

Unlocking Lossless Speedups in LLMs via Discrete Diffusion • 3 items • Updated 1 day ago • 2