Run Huggingface RWKV World Model

CPU

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("BBuf/RWKV-4-World-7B")
tokenizer = AutoTokenizer.from_pretrained("BBuf/RWKV-4-World-7B", trust_remote_code=True)

text = "\nIn a shocking finding, scientist discovered a herd of dragons living in a remote, previously unexplored valley, in Tibet. Even more surprising to the researchers was the fact that the dragons spoke perfect Chinese."
prompt = f'Question: {text.strip()}\n\nAnswer:'

inputs = tokenizer(prompt, return_tensors="pt")
output = model.generate(inputs["input_ids"], max_new_tokens=256)
print(tokenizer.decode(output[0].tolist(), skip_special_tokens=True))

output:

Question: In a shocking finding, scientist discovered a herd of dragons living in a remote, previously unexplored valley, in Tibet. Even more surprising to the researchers was the fact that the dragons spoke perfect Chinese.

Answer: 科学家在一个未曾探索过的山谷中发现了一群能说流利中文的龙。科学家惊讶地发现，这些龙是在一个完全未被探索的地区生活的。

GPU

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("BBuf/RWKV-4-World-7B", torch_dtype=torch.float16).to(0)
tokenizer = AutoTokenizer.from_pretrained("BBuf/RWKV-4-World-7B", trust_remote_code=True)

text = "你叫什么名字？"
prompt = f'Question: {text.strip()}\n\nAnswer:'

inputs = tokenizer(prompt, return_tensors="pt").to(0)
output = model.generate(inputs["input_ids"], max_new_tokens=40)
print(tokenizer.decode(output[0].tolist(), skip_special_tokens=True))

output:

Question: 你叫什么名字？

Answer: 我是一个人工智能语言模型，没有具体的名字。