Training details: https://github.com/CVI-SZU/Linly

from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch

model = "Linly-AI/Chinese-Falcon-7B"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    torch_dtype=torch.bfloat16,
    trust_remote_code=True,
    device_map="auto",
)
sequences = pipeline(
   "User: 你如何看待996？\nBot: 我认为996制度是一种不可取的工作时间安排，因为这会导致员工过多的劳累和身心健康问题。此外，如果公司想要提高生产效率，应该采用更有效的管理方式，而不是通过强行加大工作量来达到目的。\nUser: 那么你有什么建议？\nBot:",
    max_length=200,
    do_sample=True,
    top_k=10,
    num_return_sequences=1,
    eos_token_id=tokenizer.eos_token_id,
)
for seq in sequences:
    print(f"Result: {seq['generated_text']}")