gpt2-rlhf-reward

作者 sugam11 · 下载 212 · 点赞 4 · 更新 2023-11-01

from transformers import AutoTokenizer, GPT2ForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("microsoft/DialogRPT-updown")
model = GPT2ForSequenceClassification.from_pretrained("sugam11/gpt2-rlhf-reward")
inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
with torch.no_grad():
  logits = model(**inputs).logits

模型信息

该模型卡暂无预览图和文字说明。以下信息来自 Hugging Face。

作者 sugam11
类型—
基础模型—
标签—
下载212
点赞4
更新时间2023-11-01
Hugging Face https://huggingface.co/sugam11/gpt2-rlhf-reward