from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("svjack/bloom-daliy-dialogue")
model = AutoModelForCausalLM.from_pretrained("svjack/bloom-daliy-dialogue")
tokenizer.decode(
model.generate(
tokenizer.encode(
"你饿吗?", return_tensors="pt", add_special_tokens=True
), max_length = 128)[0],
skip_special_tokens = True
).split("\n-----\n")
'''
['你饿吗?',
'我饿了',
'你想吃点什么吗?',
'我可能也饿了',
'你想吃块蛋糕吗?',
'这听起来不错',
'你要什么蛋糕?',
'我也不知道啊 第一次来这里',
'让我看看... 这是什么蛋糕?',
'是软软糖圣菲利斯蛋糕。',
'你吃了多少?',
'我大概应该吃一小百二十块。',
'你通常吃哪种蛋糕?',
'我通常只吃一点。',
'你知道,我不喜欢吃软糖圣菲利斯蛋糕。',
'你有什么特别喜欢']
'''
- Downloads last month
- 10
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.