Instructions to use RWKV-Red-Team/ARWKV-R1-1B5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RWKV-Red-Team/ARWKV-R1-1B5 with Transformers:

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

pipe = pipeline("text-generation", model="RWKV-Red-Team/ARWKV-R1-1B5", 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-R1-1B5", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RWKV-Red-Team/ARWKV-R1-1B5 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-R1-1B5"
# 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-R1-1B5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RWKV-Red-Team/ARWKV-R1-1B5

SGLang

How to use RWKV-Red-Team/ARWKV-R1-1B5 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-R1-1B5" \
    --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-R1-1B5",
		"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-R1-1B5" \
        --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-R1-1B5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RWKV-Red-Team/ARWKV-R1-1B5 with Docker Model Runner:
```
docker model run hf.co/RWKV-Red-Team/ARWKV-R1-1B5
```

Alic-Li commited on Feb 11, 2025

Commit

cd799b3

verified ·

1 Parent(s): 7a0f80a

Delete ✈️ Benchmark

Browse files

Files changed (1) hide show

README.md +0 -9

README.md CHANGED Viewed

@@ -110,15 +110,6 @@ The largest rainforest located in South America is the Amazon. It is named after
 | Training Tokens | 40M | Distillation-focused |
 | Precision | FP16 inference recommended(16G Vram required) | 15%↑ vs BF16 |
-## ✈️ Benchmark
-|           |Qwen2.5-7B-Instruct|ARWKV_7B         |ARWKV_R1_7B     |
-|-----------|-------------------|-----------------|----------------|
-|MMLU       |` 71.72 `          |` 62.41 `        |` 67.25 `   ↗️  |
-|GSM8K      |` 71.35 `          |` 68.67 `        |` 56.06 `   ↘️  |
-|WinoGrande |` 82.34 `          |` 39.95 `        |` 51.93 `   ↗️  |
-|IfEval     |` 73.62 `          |` 52.16 `        |` 60.31 `   ↗️  |
-|Arc-c      |` 54.86 `          |` 52.22 `        |` 29.01 `   ↘️  |
 ## 🏗️ Architecture Highlights
 ### Core Modification Flow
 ```diff

 | Training Tokens | 40M | Distillation-focused |
 | Precision | FP16 inference recommended(16G Vram required) | 15%↑ vs BF16 |
 ## 🏗️ Architecture Highlights
 ### Core Modification Flow
 ```diff