Instructions to use RWKV/RWKV7-Goose-Pile-421M-HF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RWKV/RWKV7-Goose-Pile-421M-HF with Transformers:

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

pipe = pipeline("text-generation", model="RWKV/RWKV7-Goose-Pile-421M-HF", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("RWKV/RWKV7-Goose-Pile-421M-HF", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use RWKV/RWKV7-Goose-Pile-421M-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-Pile-421M-HF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RWKV/RWKV7-Goose-Pile-421M-HF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RWKV/RWKV7-Goose-Pile-421M-HF

SGLang

How to use RWKV/RWKV7-Goose-Pile-421M-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-Pile-421M-HF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RWKV/RWKV7-Goose-Pile-421M-HF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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-Pile-421M-HF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RWKV/RWKV7-Goose-Pile-421M-HF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RWKV/RWKV7-Goose-Pile-421M-HF with Docker Model Runner:
```
docker model run hf.co/RWKV/RWKV7-Goose-Pile-421M-HF
```

rwkv7-421M-pile

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
License: Apache-2.0
Parameter count: 421M
Tokenizer: GPT-NeoX 20B tokenizer

Model Sources

Repository: https://github.com/fla-org/flash-linear-attention ; https://github.com/BlinkDL/RWKV-LM
Paper: RWKV: Parallelizable RNN with Transformer-level LLM Performance
Project Page: RWKV

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/rwkv7-421M-pile', trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained('fla-hub/rwkv7-421M-pile', trust_remote_code=True)

Training Details

Training Data

This model is trained on the Pile with a total of 332 billion tokens.

Training Hyperparameters

Training regime: bfloat16, lr 8e-4 to 3e-5 cosine decay, wd 0.1, bsz 8x30x4096

Evaluation

Metrics

lambada_openai: ppl 7.21 acc 57.9%

piqa: acc 69.2%

FAQ

Q: safetensors metadata is none.

A: upgrade transformers to >=4.48.0: pip install 'transformers>=4.48.0'

Downloads last month: 67

Safetensors

Model size

0.4B params

Tensor type

BF16

Model tree for RWKV/RWKV7-Goose-Pile-421M-HF

Base model

BlinkDL/rwkv-7-pile

Finetuned

(6)

this model

Dataset used to train RWKV/RWKV7-Goose-Pile-421M-HF

Collection including RWKV/RWKV7-Goose-Pile-421M-HF

RWKV v7

Collection

9 items • Updated Mar 17, 2025 • 12

Paper for RWKV/RWKV7-Goose-Pile-421M-HF

RWKV-7 "Goose" with Expressive Dynamic State Evolution

Paper • 2503.14456 • Published Mar 18, 2025 • 153