Instructions to use aabbdev/RWKV7-1.5B-20260805 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aabbdev/RWKV7-1.5B-20260805 with Transformers:

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

pipe = pipeline("text-generation", model="aabbdev/RWKV7-1.5B-20260805", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("aabbdev/RWKV7-1.5B-20260805", trust_remote_code=True, device_map="auto")

RWKV

How to use aabbdev/RWKV7-1.5B-20260805 with RWKV:

# No code snippets available yet for this library.

# To use this model, check the repository files and the library's documentation.

# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aabbdev/RWKV7-1.5B-20260805 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aabbdev/RWKV7-1.5B-20260805"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aabbdev/RWKV7-1.5B-20260805",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aabbdev/RWKV7-1.5B-20260805

SGLang

How to use aabbdev/RWKV7-1.5B-20260805 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 "aabbdev/RWKV7-1.5B-20260805" \
    --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": "aabbdev/RWKV7-1.5B-20260805",
		"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 "aabbdev/RWKV7-1.5B-20260805" \
        --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": "aabbdev/RWKV7-1.5B-20260805",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use aabbdev/RWKV7-1.5B-20260805 with Docker Model Runner:
```
docker model run hf.co/aabbdev/RWKV7-1.5B-20260805
```

aabbdev commited on 9 days ago

Commit

f118d90

verified ·

1 Parent(s): 3f174e8

Publish RWKV7-1.5B-20260805

Browse files

Files changed (2) hide show

inference/serve.py +3 -1
release-manifest.json +2 -2

inference/serve.py CHANGED Viewed

@@ -17,7 +17,9 @@ if Version(transformers.__version__) < Version("5.15"):
 from transformers.cli.serving.model_manager import ModelManager
-MODEL_ROOT = Path(__file__).resolve().parents[1]
 def _load_model_with_remote_auto(

 from transformers.cli.serving.model_manager import ModelManager
+# Hugging Face snapshots expose files as symlinks into a shared blob store.
+# `resolve()` would escape the snapshot and point at `models--OWNER--REPO`.
+MODEL_ROOT = Path(__file__).absolute().parents[1]
 def _load_model_with_remote_auto(

release-manifest.json CHANGED Viewed

@@ -87,8 +87,8 @@
     },
     "inference/serve.py": {
       "role": "inference",
-      "sha256": "00e3024bb132ffc17ffea137b07ad5434c842a5fdf4cde7f4a63d974d2d56f7c",
-      "size_bytes": 2852
     },
     "model.safetensors": {
       "role": "weights",

     },
     "inference/serve.py": {
       "role": "inference",
+      "sha256": "54484fd3a317271858d4bc8a095376990b569e2dca8676b29078f7adb42c64c9",
+      "size_bytes": 3005
     },
     "model.safetensors": {
       "role": "weights",