Instructions to use wangyue114514/rwkv7-g1g-7.2b-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wangyue114514/rwkv7-g1g-7.2b-hf with Transformers:

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

pipe = pipeline("text-generation", model="wangyue114514/rwkv7-g1g-7.2b-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("wangyue114514/rwkv7-g1g-7.2b-hf", trust_remote_code=True, device_map="auto")

RWKV

How to use wangyue114514/rwkv7-g1g-7.2b-hf 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 wangyue114514/rwkv7-g1g-7.2b-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wangyue114514/rwkv7-g1g-7.2b-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": "wangyue114514/rwkv7-g1g-7.2b-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/wangyue114514/rwkv7-g1g-7.2b-hf

SGLang

How to use wangyue114514/rwkv7-g1g-7.2b-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 "wangyue114514/rwkv7-g1g-7.2b-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": "wangyue114514/rwkv7-g1g-7.2b-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 "wangyue114514/rwkv7-g1g-7.2b-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": "wangyue114514/rwkv7-g1g-7.2b-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use wangyue114514/rwkv7-g1g-7.2b-hf with Docker Model Runner:
```
docker model run hf.co/wangyue114514/rwkv7-g1g-7.2b-hf
```

RWKV-7 G1G 7.2B — Hugging Face reference model

This repository is a self-contained Hugging Face conversion of rwkv7-g1g-7.2b-20260523-ctx8192.pth. Release v0.9.0 contains the complete readable, pure-PyTorch reference implementation next to the weights. Normal inference does not require rwkv7-hf, FLA, a custom CUDA wheel, JIT, or CUDA Graphs.

Install and use

python -m pip install torch transformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "wangyue114514/rwkv7-g1g-7.2b-hf"
revision = "v0.9.0"
tokenizer = AutoTokenizer.from_pretrained(
    model_id, revision=revision, trust_remote_code=True
)
model = AutoModelForCausalLM.from_pretrained(
    model_id, revision=revision, trust_remote_code=True, torch_dtype="auto"
).eval()
device = "cuda" if torch.cuda.is_available() else "cpu"
model = model.to(device)
inputs = tokenizer("The future of recurrent language models is", return_tensors="pt")
inputs = {key: value.to(device) for key, value in inputs.items()}
with torch.inference_mode():
    tokens = model.generate(**inputs, max_new_tokens=32)
print(tokenizer.decode(tokens[0], skip_special_tokens=True))

trust_remote_code=True loads the checked-in files configuration_rwkv7.py, cache_rwkv7.py, ops_rwkv7.py, modeling_rwkv7.py, and tokenization_rwkv7.py. The recurrent state has the canonical [batch, heads, key, value] layout. Cache lifecycle, loss, padding, generation, gradients, and the layer structure are visible in those files.

Fine-tuning and evaluation

The model follows the standard AutoModelForCausalLM contract and supports Trainer, Accelerate, PEFT LoRA, TRL SFT/DPO/GRPO, and lm_eval through the ordinary Transformers path. Set model.config.use_cache = False during training. Reproducible examples and evaluation manifests are in 123123213weqw/hf-adapter.

Reference versus optimized execution

The v0.9.0 model code intentionally favors readability and compatibility. It is the correctness/reference path, not a peak-throughput benchmark backend. Optional CUDA Graph and Triton work is maintained separately on perf/optional-native-backend-v0.10; older CUDA/JIT/quantization and KV-v2 experiments remain on perf/native-kernels-v0.8. Neither branch changes this model repository's public HF contract.

Model and provenance

Architecture: RWKV-7 recurrent causal language model
Checkpoint family: G1G
Parameters: 7,199,141,888
Layers: 32
Hidden size: 4096
Vocabulary size: 65536
Stored weight dtype: float16
Original checkpoint SHA256: 425fc9bda2d12d4ce3b6bfe5c3b3f355be8b14d85960cf40fcca58a19d632630
Reference source revision: b8438cab0dc7d11238942efca4c05135d53fcaf8
Release tag: v0.9.0

conversion_manifest.json retains the immutable original conversion and weight provenance. v0.9.0 changes the checked-in runtime code and config only; the safetensors bytes are not rewritten or re-uploaded.

License

Apache-2.0. See LICENSE.

Downloads last month: 605

Safetensors

Model size

7B params

Tensor type

F16

Collection including wangyue114514/rwkv7-g1g-7.2b-hf

RWKV7-G1 Transformers

Collection

RWKV7-G1 FP16 Transformers models (0.1B-13.3B) for rwkv7-hf 0.8.1, with the unified convert, doctor, exact CUDA-wheel discovery, and smoke CLI. • 6 items • Updated about 1 month ago