llama-moe/LLaMA-MoE-v1-3_5B-2_8-sft

# python>=3.10

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_dir = "llama-moe/LLaMA-MoE-v1-3_5B-2_8-sft"
tokenizer = AutoTokenizer.from_pretrained(model_dir, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_dir, torch_dtype=torch.bfloat16, trust_remote_code=True)
model.eval()
model.cuda()

input_text = "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. human: Give me a three-day plan in Suzhou. gpt:"
inputs = tokenizer(input_text, return_tensors="pt")
input_ids = inputs["input_ids"].cuda()

pred = model.generate(input_ids, max_length=100, temperature=1.0, do_sample=True, use_cache=True)
print(tokenizer.decode(pred.cpu()[0], skip_special_tokens=True))
"""
Sure, I can provide you with a three-day itinerary in Suzhou. Here's what we can do:

Day 1:

* Visit Suzhou Industrial Park, a major commercial and manufacturing district ...
"""

@article{llama-moe,
  title={LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training},
  author={Tong Zhu and Xiaoye Qu and Daize Dong and Jiacheng Ruan and Jingqi Tong and Conghui He and Yu Cheng},
  journal={arXiv preprint arXiv:2406.16554},
  year={2024},
  url={https://arxiv.org/abs/2406.16554},
}