Instructions to use featherless-ai/QRWKV-72B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use featherless-ai/QRWKV-72B with Transformers:

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

pipe = pipeline("text-generation", model="featherless-ai/QRWKV-72B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("featherless-ai/QRWKV-72B", trust_remote_code=True, device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use featherless-ai/QRWKV-72B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "featherless-ai/QRWKV-72B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "featherless-ai/QRWKV-72B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/featherless-ai/QRWKV-72B

SGLang

How to use featherless-ai/QRWKV-72B 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 "featherless-ai/QRWKV-72B" \
    --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": "featherless-ai/QRWKV-72B",
		"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 "featherless-ai/QRWKV-72B" \
        --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": "featherless-ai/QRWKV-72B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use featherless-ai/QRWKV-72B with Docker Model Runner:
```
docker model run hf.co/featherless-ai/QRWKV-72B
```

Add link to paper

by nielsr HF Staff - opened Jun 8, 2025

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

-0

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -9,6 +9,7 @@ library_name: transformers
 - Try out the model on [![Featherless](https://img.shields.io/badge/featherless--ai%2FQwerky--72B-Dummy?style=flat&label=Featherless&color=facc15)](https://featherless.ai/models/featherless-ai/Qwerky-72B)
 - Model details from our blog post here! [![Substack](https://img.shields.io/badge/Substack-Dummy?style=flat&color=facc15)](https://substack.recursal.ai/p/qwerky-72b-and-32b-training-large)
 Benchmarks is as follows for both Qwerky-QwQ-32B and Qwerky-72B models:

 - Try out the model on [![Featherless](https://img.shields.io/badge/featherless--ai%2FQwerky--72B-Dummy?style=flat&label=Featherless&color=facc15)](https://featherless.ai/models/featherless-ai/Qwerky-72B)
 - Model details from our blog post here! [![Substack](https://img.shields.io/badge/Substack-Dummy?style=flat&color=facc15)](https://substack.recursal.ai/p/qwerky-72b-and-32b-training-large)
+- This model was presented in [RADLADS: Rapid Attention Distillation to Linear Attention Decoders at Scale](https://huggingface.co/papers/2505.03005).
 Benchmarks is as follows for both Qwerky-QwQ-32B and Qwerky-72B models: