alt.freeweights.text / IndustryCorpus2_Classifier
From: BAAI <huggingface.co/BAAI>Newsgroups: alt.freeweights.textSubject:

IndustryCorpus2_Classifier

Date: 2026-11-15Commit: c3e596fSigned: 2DC28CC7B26A283B ✓

Model with 568M parameters. Safetensors weights, 2.29 GB in all. Published by BAAI under Apache-2.0.

568M params2.29GBIndustryCorpus2_Classifiersafetensorspermissive
FactsParams568MSize2.29 GBFormatssafetensorsTasknot taggedLicenseApache-2.0From sourcepermissive
$ fw get BAAI/IndustryCorpus2_Classifier
# manifest sha256 beb3147e4a38… · 2.29 GB · 13 files
$ fw verify ./IndustryCorpus2_Classifier BAAI/IndustryCorpus2_Classifier
From sourceHosted (signed)BAAI/IndustryCorpus2_ClassifierLast check: 2026-11-15 04:14 UTC

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Fine-tune of bge-m3.

Works with

Runs with

Ranked by fit to this model (safetensors), then by GitHub stars.

Overview

Size
2.29 GB
Weights
2.27 GB (safetensors)
Parameters
568M
Formats
safetensors
Task
not tagged
License
Apache-2.0 (permissive)
Files
13, each with a sha256
Publisher
BAAI
Added
2026-11-15
Section
alt.freeweights.text
Lineage

Original release from the publisher.

Base model: BAAI/bge-m3

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 04:14 UTCpassed

Model card

From the publisher at commit c3e596f. Shown as plain text with links; images open at the publisher.

该模型是数据集BAAI/IndustryCorpus2用于31个行业分类

模型细节:#

为了提升数据集中行业划分对实际行业的覆盖,并对齐国家标准中定义的行业目录,我们参考国家统计局制定的国民经济行业分类体系和世界知识体系,进行类目的合并和整合,设计了覆盖中英文的最终的31个行业类目。类目表名称如下所示

{
    "数学_统计": {"zh": "数学与统计", "en": "Math & Statistics"},
    "体育": {"zh": "体育", "en": "Sports"},
    "农林牧渔": {"zh": "农业与渔业", "en": "Agriculture & Fisheries"},
    "房地产_建筑": {"zh": "房地产与建筑", "en": "Real Estate & Construction"},
    "时政_政务_行政": {"zh": "政治与行政", "en": "Politics & Administration"},
    "消防安全_食品安全": {"zh": "安全管理", "en": "Safety Management"},
    "石油化工": {"zh": "石油化工", "en": "Petrochemicals"},
    "计算机_通信": {"zh": "计算机与通信", "en": "Computing & Telecommunications"},
    "交通运输": {"zh": "交通运输", "en": "Transportation"},
    "其他": {"zh": "其他", "en": "Others"},
    "医学_健康_心理_中医": {"zh": "健康与医学", "en": "Health & Medicine"},
    "文学_情感": {"zh": "文学与情感", "en": "Literature & Emotions"},
    "水利_海洋": {"zh": "水利与海洋", "en": "Water Resources & Marine"},
    "游戏": {"zh": "游戏", "en": "Gaming"},
    "科技_科学研究": {"zh": "科技与研究", "en": "Technology & Research"},
    "采矿": {"zh": "采矿", "en": "Mining"},
    "人工智能_机器学习": {"zh": "人工智能", "en": "Artificial Intelligence"},
    "其他信息服务_信息安全": {"zh": "信息服务", "en": "Information Services"},
    "学科教育_教育": {"zh": "学科教育", "en": "Subject Education"},
    "新闻传媒": {"zh": "新闻传媒", "en": "Media & Journalism"},
    "汽车": {"zh": "汽车", "en": "Automobiles"},
    "生物医药": {"zh": "生物医药", "en": "Biopharmaceuticals"},
    "航空航天": {"zh": "航空航天", "en": "Aerospace"},
    "金融_经济": {"zh": "金融与经济", "en": "Finance & Economics"},
    "住宿_餐饮_酒店": {"zh": "住宿与餐饮", "en": "Hospitality & Catering"},
    "其他制造": {"zh": "制造业", "en": "Manufacturing"},
    "影视_娱乐": {"zh": "影视与娱乐", "en": "Film & Entertainment"},
    "旅游_地理": {"zh": "旅游与地理", "en": "Travel & Geography"},
    "法律_司法": {"zh": "法律与司法", "en": "Law & Justice"},
    "电力能源": {"zh": "电力与能源", "en": "Power & Energy"},
    "计算机编程_代码": {"zh": "编程", "en": "Programming"},
}

行业分类模型的数据构造#

  • 数据构建
    • 数据来源:预训练预训练语料抽样和开源文本分类数据,其中预训练语料占比90%,通过数据采样,保证中英文数据占比为1:1
    • 标签构造:使用LLM模型对数据进行多次分类判定,筛选多次判定一致的数据作为训练数据
    • 数据规模:36K 数据构造的整体流程如下: Image: image-20240919140307205

模型训练:#

参数更新:在预训练的bert模型上添加分类头进行文本分类模型训练

模型选型:考虑的模型性能和推理效率,我们选用了0.5b规模的模型,通过对比实验最终最终选择了bge-m3并全参数训练的方式,作为我们的基座模型

训练超参:全参数训练,max_length = 2048,lr=1e-5,batch_size=64,,验证集评估acc:86%

Image: image-20240919141408659

how to use#

from transformers import (
    AutoConfig,
    AutoModelForSequenceClassification,
    AutoTokenizer)
import torch

model_dir = "BAAI/IndustryCorpus2_Classifier"

model = AutoModelForSequenceClassification.from_pretrained(
      model_dir,
      trust_remote_code=False,
      ignore_mismatched_sizes=False,
).half().cuda().eval()

tokenizer = AutoTokenizer.from_pretrained(
    model_dir,
    use_fast=True,
    token=None,
    trust_remote_code=False,
)

config = AutoConfig.from_pretrained(
    model_dir,
    finetuning_task="text-classification",
)

id2label = config.id2label
print(id2label)
label2id = config.label2id
print(label2id)


sentence = "黄龙国际中心位于杭州市西湖区学院路77号,地处杭州黄龙商务区核心位置。项目以“新经济、新生态、新黄龙”的理念和“知识城市创新区”的项目定位,引领着杭州城市的产业升级和创新。\n黄龙国际中心主打“知识盒子”建筑设计,拥有时尚、新潮的建筑立面,聚集不同功能的独立建筑物,打造出包容开放又具有链接性的空间。项目在2018年4月一举斩获开发项目行业最高奖——广厦奖。\n项目整体分四期开发。一期G、H、I三幢楼宇由坤和自主开发建成,于2015年4月投入使用,于2015年5月获得了美国绿色建筑委员会颁发的LEED金级认证,并成功吸引蚂蚁金服、美图、有赞等国内互联网创新巨头率先入驻。\n2016年初,坤和引进万科作为该项目股权合作方通过双方优质资源共享,在产品品质、创新等方面得到全方位提升。\n二期A、B幢由美国KPF设计,并于2018年4月一举获得房地产开发项目行业最高奖——广厦奖。A、B幢写字楼于2018年10月投入使用,B幢与全球领先的创造者社区及空间和服务提供商——WeWork正式签约。商业K-lab于2018年12月28日正式开业。\n项目三期E、F幢已于2020年投入使用。四期C、D幢,计划于2021年底投入使用。\n项目总占地面积约8.7万方,总建筑面积约40万平方米,涵盖9栋国际5A写字楼及8万方K-lab商业新物种,以知识为纽带,打造成一个集商务、商业、教育、文化、娱乐、艺术、餐饮、会展等于一体的完整城市性生态体系。项目全部投入使用后,年租金收入将超6亿元。\n"

result = tokenizer(
            [sentence],
            padding=False,
            max_length=2048,
            truncation=True,
            return_tensors="pt",
        ).to("cuda")
result["input_ids"].to(dtype=torch.bfloat16)

model_out = model(**result)
predict_label_id = torch.argmax(model_out.logits, dim=-1).tolist()[0]
predict_label_str = id2label[predict_label_id]

Citation#

If you use this classifier or IndustryCorpus2, please cite the source dataset:

@misc{shi2024industrycorpus2,
  title     = {IndustryCorpus2},
  author    = {Xiaofeng Shi and Lulu Zhao and Hua Zhou and Donglin Hao},
  year      = {2024},
  publisher = {Hugging Face},
  doi       = {10.57967/hf/3488},
  url       = {https://huggingface.co/datasets/BAAI/IndustryCorpus2}
}

Files

13 files · 2.29 GBWeights 2.27 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 13 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md6.94 KB9ecead44a1ffc1d87039457e315ccd2594afdfd16cded5e3c4940e1386f5d6a9
config.json3.42 KBceb88e2326b332ed97f3833edae510f8cee0058c82acc9a0a3c6ac14947a167f
img/.DS_Store6.15 KB442780a79db09250aaac14d27f1ab661857dca8fe5ba10b5858078a43f7fe3ae
img/classify.png47.6 KBf61ddfe8a9b1820de0abe48e121ea0d5751da87b7f8368bbf2ded14c6c925ff5
img/classify_exp.png46.9 KBe901a8c1d21e7c5693cc3939cd674a21b2b1c9d8bf4c53cc64750eb3134975bf
model.safetensors2.27 GB0597708ae15fdcce27850e947653857d31f2e161a0ff46c53185ad58b644908c
sentencepiece.bpe.model5.07 MBcfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
special_tokens_map.json964 B8c785abebea9ae3257b61681b4e6fd8365ceafde980c21970d001e834cf10835
tokenizer.json17.1 MB6710678b12670bc442b99edc952c4d996ae309a7020c1fa0096dd245c2faf790
tokenizer_config.json1.17 KB7e4c1cc848840aeccdd763458c18dd525eb0f795c992e00ebe9c28554e7db2d4
trainer_state.json537 KBf9874523712554248b44da1e536f4d9cd5ba16c3642fa0254bab3c8ba804290b
training_args.bin5.24 KB16a60324779f4561552c1e524383f6591f97b80e0adc5098445a110a72360d23
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
c3e596f92a pinned now2026-11-15 04:14 UTC13 files · 2.29 GB

Use it

$ fw get BAAI/IndustryCorpus2_Classifier
# manifest sha256 beb3147e4a38… · 2.29 GB · 13 files
$ fw verify ./IndustryCorpus2_Classifier BAAI/IndustryCorpus2_Classifier
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/BAAI/IndustryCorpus2_Classifier.json --dir ./IndustryCorpus2_Classifier $ python3 fw.py verify ./IndustryCorpus2_Classifier ./BAAI__IndustryCorpus2_Classifier.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download BAAI/IndustryCorpus2_Classifier --revision c3e596f92a4616769a4111a04c57886a1f2b9655 --local-dir ./IndustryCorpus2_Classifier

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-15
Text in
README.md
Text sha256
9ecead44a1ffc1d87039457e315ccd2594afdfd16cded5e3c4940e1386f5d6a9
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: BAAI <huggingface.co/BAAI>Newsgroups: alt.freeweights.textSubject: IndustryCorpus2_ClassifierDate: 2026-11-15Commit: c3e596fSigned: 2DC28CC7B26A283B ✓
Upstream
BAAI/IndustryCorpus2_Classifier
Pinned commit
c3e596f92a4616769a4111a04c57886a1f2b9655
Manifest
IndustryCorpus2_Classifier.json · .minisig
Manifest sha256
beb3147e4a3801954543463c3050ad828fcad83b97696d6a3b642d6538a0db2e
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:14 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/BAAI/IndustryCorpus2_Classifier.json $ curl -O https://freeweights.allternit.com/manifests/BAAI/IndustryCorpus2_Classifier.json.minisig $ minisign -Vm IndustryCorpus2_Classifier.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

Parent

BAAI/bge-m3 · this model is a finetune of it

No model in the catalog names this one as its parent.

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download BAAI/IndustryCorpus2_Classifier
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. IndustryCorpus2_Classifier.json. Provenance. Takedown history: none.
From: laion <huggingface.co/laion>Subject: a2-rl-e2egit_large-50-32B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-large-15-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_pymethods2test-large-80-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_unitsyn-python-large-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_mix_h2_language_proportional-65-8B