Edit model card

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/

Downloads last month
4
Inference API
Unable to determine this model’s pipeline type. Check the docs .