hf_mirrors/Yuan2.0-2B-hf
Model Introduction
Files & versions
Analysis

Yuan 2-2B

模型介绍/Introduction

源2.0 是浪潮信息发布的新一代基础语言大模型。我们开源了全部的3个模型源2.0-102B,源2.0-51B和源2.0-2B。并且我们提供了预训练,微调,推理服务的相关脚本,以供研发人员做进一步的开发。源2.0是在源1.0的基础上,利用更多样的高质量预训练数据和指令微调数据集,令模型在语义、数学、推理、代码、知识等不同方面具备更强的理解能力。

Yuan2.0 is a new generation Fundamental Large Language Model developed by IEIT System. We have published all three models, Yuan 2.0-102B, Yuan 2.0-51B, and Yuan 2.0-2B. And we provide relevant scripts for pretraining, fine-tuning, and inference services for other developers. Yuan2.0 is based on Yuan1.0, utilizing a wider range of high-quality pre training data and instruction fine-tuning datasets to enhance the model's understanding of semantics, mathematics, reasoning, code, knowledge, and other aspects.

代码调用/Code Usage

可以通过如下代码调用 Yuan2-2B 模型来生成文本:

You can generate text by invoking the Yuan2-2B model with the following code:

import transformers
from transformers import AutoModelForCausalLM,AutoTokenizer,LlamaTokenizer
from openmind_hub import snapshot_download
import torch
import torch_npu
import argparse

def parse_args():
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--model_name_or_path",
        type=str,
        help="path_model",
        default="Jinan_AICC/Yuan2.0-2B-hf",
    )
    args = parser.parse_args()
    return args

args = parse_args()
if args.model_name_or_path:
    model_path = args.model_name_or_path
else:
    model_path = snapshot_download(
        "Jinan_AICC/Yuan2.0-2B-hf",
        revision="main",
        ignore_patterns=["*.h5", "*.ot", "*.msgpack"],       
    )

print("Creat tokenizer...")
tokenizer = LlamaTokenizer.from_pretrained(model_path, add_eos_token=False, add_bos_token=False, eos_token='<eod>')
tokenizer.add_tokens(['<sep>', '<pad>', '<mask>', '<predict>', '<FIM_SUFFIX>', '<FIM_PREFIX>', '<FIM_MIDDLE>','<commit_before>','<commit_msg>','<commit_after>','<jupyter_start>','<jupyter_text>','<jupyter_code>','<jupyter_output>','<empty_output>'], special_tokens=True)

print("Creat model...")
model = AutoModelForCausalLM.from_pretrained(model_path,device_map='auto',torch_dtype=torch.bfloat16,trust_remote_code=True)

inputs = tokenizer("请问目前最先进的机器学习算法有哪些?", return_tensors="pt")["input_ids"].to("npu:0")
outputs = model.generate(inputs,do_sample=False,max_length=100)
print(tokenizer.decode(outputs[0]))