Instructions to use StarRing2022/RWKV-4-Raven-3B-v11-zh with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use StarRing2022/RWKV-4-Raven-3B-v11-zh with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("StarRing2022/RWKV-4-Raven-3B-v11-zh", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from StarRing2022/RWKV-4-Raven-3B-v11-zh: direct link, hf CLI and curl.
- Browser
- Download file 764 Bytes
-
https://huggingface.co/StarRing2022/RWKV-4-Raven-3B-v11-zh/resolve/main/README.md
- Command line
-
hf download hf://StarRing2022/RWKV-4-Raven-3B-v11-zh/README.md
-
curl -L -o README.md https://huggingface.co/StarRing2022/RWKV-4-Raven-3B-v11-zh/resolve/main/README.md
764 Bytes
metadata
RWKV-4-Raven-3B-v11-zh: null
将RWKV模型转化为HF格式,与HF无缝连接,几句代码调用RWKV 底座模型:RWKV-4-Raven-3B-v11-Eng49%-Chn49%-Jpn1%-Other1%-20230429-ctx4096.pth(https://huggingface.co/BlinkDL/rwkv-4-raven)
import torch
from transformers import GPTNeoXTokenizerFast, RwkvConfig, RwkvForCausalLM
model = RwkvForCausalLM.from_pretrained("StarRing2022/RWKV-4-Raven-3B-v11-zh")
tokenizer = GPTNeoXTokenizerFast.from_pretrained("StarRing2022/RWKV-4-Raven-3B-v11-zh")
text = "你好"
input_ids = tokenizer.encode(text, return_tensors='pt')
out = model.generate(input_ids=input_ids,max_new_tokens=128)
answer = tokenizer.decode(out[0])
print(answer)
GIT开源地址:https://github.com/StarRing2022/HF-For-RWKVRaven-Alpaca/