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, dtype="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

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 pipeline tag

by nielsr HF Staff - opened Jun 8, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-3

Files changed (1) hide show

README.md +4 -3

README.md CHANGED Viewed

@@ -1,8 +1,9 @@
 ---
-thumbnail: https://cdn-uploads.huggingface.co/production/uploads/633e85093a17ab61de8d9073/dM-i7n313mUnY-fbmElVM.png
 license: other
 license_name: tongyi-qianwen
-library_name: transformers
 ---
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/633e85093a17ab61de8d9073/dM-i7n313mUnY-fbmElVM.png)
@@ -82,4 +83,4 @@ As demonstrated with our Qwerky-72B-Preview and prior models such as QRWKV6-32B
 As with our previous models, the model's inherent knowledge and dataset training are inherited from its "parent" model. Consequently, unlike previous RWKV models trained on over 100+ languages, the QRWKV model is limited to approximately 30 languages supported by the Qwen line of models.
-You may find our details of the process from our previous release, [here](https://huggingface.co/recursal/QRWKV6-32B-Instruct-Preview-v0.1).

 ---
+library_name: transformers
 license: other
 license_name: tongyi-qianwen
+thumbnail: https://cdn-uploads.huggingface.co/production/uploads/633e85093a17ab61de8d9073/dM-i7n313mUnY-fbmElVM.png
+pipeline_tag: text-generation
 ---
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/633e85093a17ab61de8d9073/dM-i7n313mUnY-fbmElVM.png)
 As with our previous models, the model's inherent knowledge and dataset training are inherited from its "parent" model. Consequently, unlike previous RWKV models trained on over 100+ languages, the QRWKV model is limited to approximately 30 languages supported by the Qwen line of models.
+You may find our details of the process from our previous release, [here](https://huggingface.co/recursal/QRWKV6-32B-Instruct-Preview-v0.1).