Instructions to use RWKV-Red-Team/ARWKV-7B-Preview-0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RWKV-Red-Team/ARWKV-7B-Preview-0.1 with Transformers:

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

pipe = pipeline("text-generation", model="RWKV-Red-Team/ARWKV-7B-Preview-0.1", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("RWKV-Red-Team/ARWKV-7B-Preview-0.1", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RWKV-Red-Team/ARWKV-7B-Preview-0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RWKV-Red-Team/ARWKV-7B-Preview-0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RWKV-Red-Team/ARWKV-7B-Preview-0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RWKV-Red-Team/ARWKV-7B-Preview-0.1

SGLang

How to use RWKV-Red-Team/ARWKV-7B-Preview-0.1 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 "RWKV-Red-Team/ARWKV-7B-Preview-0.1" \
    --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": "RWKV-Red-Team/ARWKV-7B-Preview-0.1",
		"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 "RWKV-Red-Team/ARWKV-7B-Preview-0.1" \
        --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": "RWKV-Red-Team/ARWKV-7B-Preview-0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RWKV-Red-Team/ARWKV-7B-Preview-0.1 with Docker Model Runner:
```
docker model run hf.co/RWKV-Red-Team/ARWKV-7B-Preview-0.1
```

zhiyuan8 commited on May 11, 2025

Commit

55d2dd9

verified ·

1 Parent(s): 1617bfc

Update wkv.py

Browse files

Files changed (1) hide show

wkv.py +1 -1

wkv.py CHANGED Viewed

@@ -282,7 +282,7 @@ class Rwkv_Tmix_x070(nn.Module):
             self.a0 + (xa @ self.a1) @ self.a2
         )  # a is "in-context learning rate"
         if self.args.wkv_has_gate:
-            g = torch.sigmoid(xg @ self.g1) @ self.g2 + 1.0
         kk = k * self.k_k
         kk = F.normalize(kk.view(B, T, self.n_head, -1),
                          p=2.0, dim=-1, eps=1e-4 if kk.dtype == torch.float16 else 1e-12).view(B, T, C)

             self.a0 + (xa @ self.a1) @ self.a2
         )  # a is "in-context learning rate"
         if self.args.wkv_has_gate:
+            g = torch.sigmoid(xg @ self.g1) @ self.g2 #+ 1.0
         kk = k * self.k_k
         kk = F.normalize(kk.view(B, T, self.n_head, -1),
                          p=2.0, dim=-1, eps=1e-4 if kk.dtype == torch.float16 else 1e-12).view(B, T, C)