Instructions to use recursal/QRWKV6-7B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use recursal/QRWKV6-7B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="recursal/QRWKV6-7B-Instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("recursal/QRWKV6-7B-Instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use recursal/QRWKV6-7B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "recursal/QRWKV6-7B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "recursal/QRWKV6-7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/recursal/QRWKV6-7B-Instruct

SGLang

How to use recursal/QRWKV6-7B-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 "recursal/QRWKV6-7B-Instruct" \
    --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": "recursal/QRWKV6-7B-Instruct",
		"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 "recursal/QRWKV6-7B-Instruct" \
        --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": "recursal/QRWKV6-7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use recursal/QRWKV6-7B-Instruct with Docker Model Runner:
```
docker model run hf.co/recursal/QRWKV6-7B-Instruct
```

Enhance model card with detailed description, usage examples, and citation

by nielsr HF Staff - opened Jul 28, 2025

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+87

-2

nielsr

Jul 28, 2025

This PR significantly improves the model card for the RADLADS model. Key updates include:

Enriched Description: Added a comprehensive overview of RADLADS, highlighting its rapid conversion protocol, efficiency, quality preservation, and new RWKV-variant architectures, drawing information from the paper's abstract and the project's GitHub README.
Visuals: Incorporated process and evaluation images from the GitHub repository to provide a clearer understanding of the model's methodology and performance.
Usage Examples: Included detailed code snippets for text generation and chat completion, making it easier for users to get started with the model using the transformers library. The examples are tailored to the model's capabilities (e.g., chat template).
Citation: Added the BibTeX entry for the RADLADS paper for proper academic attribution.
GitHub Link Verification: Confirmed and retained the GitHub repository link as https://github.com/recursal/Monet, which is the repository hosting the provided code and detailed README for the RADLADS project.

Enhance model card with detailed description, usage examples, and citation662cd934

KaraKaraWitch

recursal org Jul 28, 2025

Merged.

KaraKaraWitch changed pull request status to merged Jul 28, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment