What are the hardware requirements for Baichuan 7B Sft?

Baichuan 7B Sft requires approximately 14 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Baichuan 7B Sft and how large is it?

Baichuan 7B Sft is developed by hiyouga, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Baichuan 7B Sft?

Baichuan 7B Sft is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Baichuan 7B Sft by hiyouga — VRAM 14GB, 4K context

Name: Baichuan 7B Sft
Author: hiyouga

Baichuan 7B Sft is an open-source language model by hiyouga. Features: 7b LLM, VRAM: 14GB, Context: 4K, License: apache-2.0, LLM Explorer Score: 0.07.

Baichuan Custom code Dataset:sahil2801/codealpaca-2... Dataset:tatsu-lab/alpaca En Endpoints compatible Lora Pytorch Region:us Sharded Zh

Model Card on HF 🤗: https://huggingface.co/hiyouga/Baichuan-7B-sft

Baichuan 7B Sft Parameters and Internals

Model Type

text-generation

Additional Notes

Bilingual instruction-tuned LoRA model with training scripts provided for reproduction using LLaMA-Factory.

Supported Languages

zh (unknown), en (unknown)

Training Details

Data Sources:

tatsu-lab/alpaca, sahil2801/CodeAlpaca-20k

Methodology:

LoRA (Low-Rank Adaptation)

Input Output

Accepted Modalities:

text

LLM Name	Baichuan 7B Sft
Repository 🤗	https://huggingface.co/hiyouga/Baichuan-7B-sft
Model Size	7b
Required VRAM	14 GB
Updated	2026-08-01
Maintainer	hiyouga
Model Type	baichuan
Model Files	10.0 GB: 1-of-2 4.0 GB: 2-of-2
Supported Languages	zh en
Model Architecture	BaiChuanForCausalLM
License	apache-2.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.30.1
Tokenizer Class	BaiChuanTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	64000
LoRA Model	Yes
Torch Data Type	float16

Rank the Baichuan 7B Sft capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Baichuan 7B Sft

Best Alternatives	Context / RAM	Downloads	Likes
Baichuan 7B	4K / 14 GB	21810	841
MedChatZH	4K / 14 GB	580	9
WisdomInterrogatory	4K / 13.9 GB	14	5
Baichuan 7B Sft 001	4K / 14 GB	524	3
HuatuoGPT 7B	4K / 28 GB	819	22
Qiaoban Bc	4K / 28 GB	10	8
Baichuan 7B Instruction	4K / 14 GB	22	2
Baichuan 7B Chat	4K / 14 GB	514	25
Baichuan 7B	4K / 13.8 GB	11	0
Baichuan 7B Sharded	4K / 13.9 GB	5	1

Note: green Score (e.g. "73.2") means that the model is better than hiyouga/Baichuan-7B-sft.