Model Follower.

Up to date

Rebuilt
2026-10-25 06:54 UTC
Release radar
117 on watch
Hub snapshot
2026-10-25
Re-checked
daily · every number sourced and dated

Models › Baichuan family

Baichuan-7B

Hugging Face ↗ Follow changes

baichuan-inc Not declared out 3 years ago

Text in, text out.

Verified 2026-10-25 Rank #763 in LLMs · score 71.3 method v1 Sources 3 Downloads 30d 34.5k · #414 of 619 tracked

Can I use it?Not declaredNo license declared on the model cardlicence file
Do people use it?34.5kdownloads, 30 days#414 of 619 we track · below the median+2 likes, downloads −9% this week847 likesHugging Face

Worth reading

Picked by rule from 3 tracked pieces: the lab's own post, the most shared, a field report, the latest.

Latest · 3 years ago

Baichuan 2

Baichuan Intelligent Technology released Baichuan2-13B-Chat v2, which significantly improved the model's overall capabilities, especially in mathematics and logical reasoning, and complex instruction following.

  • The MedMCQA evaluation used the dev set because the official test set lacks answer keys.
  • HumanEval code generation evaluation was performed using a 0-shot testing configuration.
github.com 2023-10-13 1 HN pts 4.3k words about the Baichuan family family

3 best of 3 tracked

The 1 pick above, plus these 2. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.

  1. PaperBaichuan 2: Open Large-Scale Language Models. (ArXiv:2309.10305v1 [Cs.cl])arxiv.org · 2023-09-26 · 1 HN pts
  2. ArticleChina's Baichuan, Zhipu AI launch AI models after receiving approvalreuters.com · 2023-09-01 · 1 HN pts

Where it's used

Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.

No API provider serves it, so its downloads are people running it themselves: 2 quantized builds.

  • As a service0no API provider listed
  • On own hardware2quantized builds
  • Built on30 fine-tunes · 3 adapters · 0 merges
  • In apps0Hugging Face Spaces

The story so far

Weights, every dated article, and repo commits on one rail.

3 dated articles and 0 repo commits so far

Teal is the weights (2023-06-13), amber triangles are 3 dated articles (each links to it).

JulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctBaichuan 2: Open Large-Scale Language Models. (ArXiv:2309.10305v1 [Cs.cl]) · 2023-09-26Baichuan 2 · 2023-10-13China's Baichuan, Zhipu AI launch AI models after receiving approval · 2023-09-01Weights 2023-06-13 · 2023-06-13Weights 2023-06-13now
JulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctBaichuan 2: Open Large-Scale Language Models. (ArXiv:2309.10305v1 [Cs.cl]) · 2023-09-26Baichuan 2 · 2023-10-13China's Baichuan, Zhipu AI launch AI models after receiving approval · 2023-09-01Weights 2023-06-13 · 2023-06-13Weights 2023-06-13now

What people built on it

5 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.

5 derivatives on the Hub, most of them adapters

From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.

2 quantized (Hugging Face model tree)3 adapters (Hugging Face model tree)2 quantized3 adapters
2 quantized (Hugging Face model tree)3 adapters (Hugging Face model tree)2 quantized3 adapters
GGUF tensorblock/baichuan-inc_Baichuan-7B-GGUF for llama.cpp, Ollama, LM Studio 1.6k downloads

All variants →

Reference

Everything else, folded: the full tables, every source.

Facts

12 fields

Listed in LLMs

Facts

Pipeline tagtext-generation
Librarytransformers
ArchitecturesBaiChuanForCausalLM
Model typebaichuan
MoEno
PapersarXiv:1910.07467, arXiv:2009.03300
LicenseNot declared
Hub snapshot2026-10-25

All variants

5 variants

Lineage

Original model Family: baichuan-inc/Baichuan 5 derivatives on the Hub

adapter: 3quantized: 2

Top variants (5 shown, ranked by downloads)

Relation
5 rows
Variant Relation Quant Params Band License Author Likes Downloads
jeeejeee/baichuan7b-zero-init adapter — — — — jeeejeee 0 67.5k
jeeejeee/baichuan-7b-lora-zero-regex adapter — — — — jeeejeee 0 37k
tensorblock/baichuan-inc_Baichuan-7B-GGUF quantized GGUF — — — tensorblock 0 1.6k
DhruvalLabs/Baichuan-7B-GGUF quantized GGUF — — other DhruvalLabs 0 805
Sylvia2025/baichuan-7B-alpaca-gpt4-zh adapter — — — other Sylvia2025 1 74

Repository changelog

1 change
changed in the last 7 daysNew on the watch list: 2026-10-23all changes

Articles and coverage

3 pieces

Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency. Summaries are generated from a stored copy of the article text; every sentence cites a span of that text, and nothing is shown that failed the citation check.

Analysis3

Baichuan 2: Open Large-Scale Language Models. (ArXiv:2309.10305v1 [Cs.cl])
arxiv.org2023-09-26authorityabout the Baichuan familyHN 1 pts · 0 comments366 words
Baichuan 2 is a series of open multilingual large-scale language models trained from scratch on 2.6 trillion tokens. The models contain 7 billion and 13 billion parameters and match or outperform other open-source models of similar size on public benchmarks like MMLU, CMMLU, GSM8K, and HumanEval. Baichuan 2 excels in vertical domains such as medicine and law, with all pre-training model checkpoints released to benefit the research community.written, reviewed, cited
Baichuan 2
github.com2023-10-13authorityabout the Baichuan familyHN 1 pts · 0 comments4,253 words
Baichuan Intelligent Technology released Baichuan2-13B-Chat v2, which significantly improved the model's overall capabilities, especially in mathematics and logical reasoning, and complex instruction following. The release includes Base and Chat versions for 7B and 13B, and a 4bits quantized version for the Chat model. All versions are fully open to academic research, while developers only need to apply via email and obtain official commercial permission to use it for free commercially.written, reviewed, cited
  • The MedMCQA evaluation used the dev set because the official test set lacks answer keys.
  • HumanEval code generation evaluation was performed using a 0-shot testing configuration.
China's Baichuan, Zhipu AI launch AI models after receiving approval
reuters.com2023-09-01about the Baichuan familyHN 1 pts · 0 comments

Papers

2 papers

Papers 2

arXiv links found in the model card and its tags. "Peer-reviewed" is shown only with evidence: a published venue in OpenAlex (measured) or the authors' own journal reference on arXiv (reported).

Similar models

3 models

Similar models

  • opt-125m
    same task (text-generation)
  • gpt-j-6b
    same task (text-generation), permissive license
  • DialoGPT-medium
    same task (text-generation), permissive license

Sources

3 sources

Sources

Hub snapshot: 2026-10-25 · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-14 14:08 UTC · Last verified 2026-10-25

Follow Baichuan-7B

Watch this model

Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.