Instructions to use FWKV/FWKV-ROSA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FWKV/FWKV-ROSA with Transformers:

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

pipe = pipeline("text-generation", model="FWKV/FWKV-ROSA", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("FWKV/FWKV-ROSA", trust_remote_code=True, device_map="auto")

RWKV

How to use FWKV/FWKV-ROSA 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 FWKV/FWKV-ROSA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FWKV/FWKV-ROSA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FWKV/FWKV-ROSA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/FWKV/FWKV-ROSA

SGLang

How to use FWKV/FWKV-ROSA 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 "FWKV/FWKV-ROSA" \
    --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": "FWKV/FWKV-ROSA",
		"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 "FWKV/FWKV-ROSA" \
        --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": "FWKV/FWKV-ROSA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use FWKV/FWKV-ROSA with Docker Model Runner:
```
docker model run hf.co/FWKV/FWKV-ROSA
```

FlameF0X commited on 6 days ago

Commit

c9bcd25

verified ·

1 Parent(s): b8e6fd6

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -84,7 +84,7 @@ model = AutoModelForCausalLM.from_pretrained(
     "FlameF0X/FWKV-ROSA",
     trust_remote_code=True
 )
-tokenizer = AutoTokenizer.from_pretrained("FlameF0X/FWKV-ROSA")
 ```
 Then format your prompts exactly with the chat tokens:
@@ -179,7 +179,7 @@ If you use FWKV-ROSA in your research, please cite it as:
   author = {FlameF0X},
   title = {FWKV-ROSA: A 56M Recurrent Chat LM with RWKV-style Decay and ROSA Copy Signal},
   year = {2025},
-  howpublished = {\url{https://huggingface.co/FlameF0X/FWKV-ROSA}},
 }
 ```

     "FlameF0X/FWKV-ROSA",
     trust_remote_code=True
 )
+tokenizer = AutoTokenizer.from_pretrained("FWKV/FWKV-ROSA")
 ```
 Then format your prompts exactly with the chat tokens:
   author = {FlameF0X},
   title = {FWKV-ROSA: A 56M Recurrent Chat LM with RWKV-style Decay and ROSA Copy Signal},
   year = {2025},
+  howpublished = {\url{https://huggingface.co/FWKV/FWKV-ROSA}},
 }
 ```