Instructions to use fla-hub/rwkv7-2.9B-world with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fla-hub/rwkv7-2.9B-world with Transformers:

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

pipe = pipeline("text-generation", model="fla-hub/rwkv7-2.9B-world", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("fla-hub/rwkv7-2.9B-world", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fla-hub/rwkv7-2.9B-world with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fla-hub/rwkv7-2.9B-world"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fla-hub/rwkv7-2.9B-world",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fla-hub/rwkv7-2.9B-world

SGLang

How to use fla-hub/rwkv7-2.9B-world 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 "fla-hub/rwkv7-2.9B-world" \
    --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": "fla-hub/rwkv7-2.9B-world",
		"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 "fla-hub/rwkv7-2.9B-world" \
        --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": "fla-hub/rwkv7-2.9B-world",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use fla-hub/rwkv7-2.9B-world with Docker Model Runner:
```
docker model run hf.co/fla-hub/rwkv7-2.9B-world
```

Fix eos_token init and \n\n tokenization

by CISCai HF Staff - opened May 28, 2025

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

-0

Files changed (1) hide show

hf_rwkv_tokenizer.py +3 -0

hf_rwkv_tokenizer.py CHANGED Viewed

@@ -164,6 +164,9 @@ class RwkvTokenizer(PreTrainedTokenizer):
         self.encoder = vocab
         self.decoder = {v: k for k, v in vocab.items()}
         self._added_tokens_decoder = {0: AddedToken(str(bos_token))}
         super().__init__(
             bos_token=bos_token, eos_token=eos_token, unk_token=unk_token, **kwargs
         )

         self.encoder = vocab
         self.decoder = {v: k for k, v in vocab.items()}
         self._added_tokens_decoder = {0: AddedToken(str(bos_token))}
+        eos_token_bytes = str(eos_token).encode("utf-8")
+        if eos_token_bytes in vocab:
+            self._added_tokens_decoder[vocab[eos_token_bytes]] = AddedToken(str(eos_token))
         super().__init__(
             bos_token=bos_token, eos_token=eos_token, unk_token=unk_token, **kwargs
         )