Instructions to use RWKV/RWKV7-Goose-World3-1.5B-HF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RWKV/RWKV7-Goose-World3-1.5B-HF with Transformers:

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

pipe = pipeline("text-generation", model="RWKV/RWKV7-Goose-World3-1.5B-HF", 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/RWKV7-Goose-World3-1.5B-HF", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RWKV/RWKV7-Goose-World3-1.5B-HF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RWKV/RWKV7-Goose-World3-1.5B-HF"
# 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/RWKV7-Goose-World3-1.5B-HF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RWKV/RWKV7-Goose-World3-1.5B-HF

SGLang

How to use RWKV/RWKV7-Goose-World3-1.5B-HF 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/RWKV7-Goose-World3-1.5B-HF" \
    --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/RWKV7-Goose-World3-1.5B-HF",
		"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/RWKV7-Goose-World3-1.5B-HF" \
        --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/RWKV7-Goose-World3-1.5B-HF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RWKV/RWKV7-Goose-World3-1.5B-HF with Docker Model Runner:
```
docker model run hf.co/RWKV/RWKV7-Goose-World3-1.5B-HF
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

rwkv7-1.5B-world

This is RWKV-7 model under flash-linear attention format.

Model Details

Model Description

Developed by: Bo Peng, Yu Zhang, Songlin Yang, Ruichong Zhang
Funded by: RWKV Project (Under LF AI & Data Foundation)
Model type: RWKV7
Language(s) (NLP): English, Chinese, Japanese, Korean, French, Arabic, Spanish, Portuguese
License: Apache-2.0
Parameter count: 1.52B
Tokenizer: RWKV World tokenizer
Vocabulary size: 65,536

Model Sources

Repository: https://github.com/fla-org/flash-linear-attention ; https://github.com/BlinkDL/RWKV-LM
Paper: https://huggingface.co/papers/2503.14456

Uses

Install flash-linear-attention and the latest version of transformers before using this model:

pip install flash-linear-attention==0.3.0
pip install 'transformers>=4.48.0'

Direct Use

You can use this model just as any other HuggingFace models:

from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained('fla-hub/rwkv7-1.5B-world', trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained('fla-hub/rwkv7-1.5B-world', trust_remote_code=True)

model = model.cuda() # Supported on Nvidia/AMD/Intel eg. model.xpu()
prompt = "What is a large language model?"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096,
    do_sample=True,
    temperature=1.0,
    top_p=0.3,
    repetition_penalty=1.2
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=False)[0]
print(response)

Training Details

Training Data

This model is trained on the World v3 with a total of 3.119 trillion tokens.

Training Hyperparameters

Training regime: bfloat16, lr 4e-4 to 1e-5 "delayed" cosine decay, wd 0.1 (with increasing batch sizes during the middle)
Final Loss: 1.9965
Token Count: 3.119 trillion