Baichuan2 13B Chat GPTQ by TheBloke

 ยป  All LLMs  ยป  TheBloke  ยป  Baichuan2 13B Chat GPTQ   URL Share it on

  4-bit   Autotrain compatible   Baichuan Base model:baichuan-inc/baichu... Base model:quantized:baichuan-...   Custom code   En   Gptq   Quantized   Region:us   Safetensors   Zh

Baichuan2 13B Chat GPTQ Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Baichuan2 13B Chat GPTQ (TheBloke/Baichuan2-13B-Chat-GPTQ)

Baichuan2 13B Chat GPTQ Parameters and Internals

Model Type 
llama
Supported Languages 
en (English), zh (Chinese)
Training Details 
Data Volume:
2.6 trillion tokens
LLM NameBaichuan2 13B Chat GPTQ
Repository ๐Ÿค—https://huggingface.co/TheBloke/Baichuan2-13B-Chat-GPTQ 
Model NameBaichuan2-13B-Chat
Model CreatorBaichuan Intelligent Technology
Base Model(s)  Baichuan2 13B Chat   baichuan-inc/Baichuan2-13B-Chat
Model Size13b
Required VRAM9.1 GB
Updated2025-04-29
MaintainerTheBloke
Model Typebaichuan
Model Files  9.1 GB
Supported Languagesen zh
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureBaichuanForCausalLM
Licensellama2
Model Max Length4096
Transformers Version4.29.2
Tokenizer ClassBaichuanTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size125696
Torch Data Typebfloat16

Best Alternatives to Baichuan2 13B Chat GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Sakura 13B LNovel V0.8 3bit0K / 7.5 GB101
Sakura 13B LNovel V0.8 8bit0K / 9.1 GB101
Sakura 13B LNovel V0.8 4bit0K / 9.1 GB32
Baichuan2 13B Chat GPTQ Int40K / 9.1 GB102
...aichuan2 13B Chat Gptq 32g Act0K / 9.9 GB71
Baichuan 13B Instruction GPTQ0K / 7.9 GB204
Baichuan 13B Chat 8bit0K / 14.1 GB159
Tiny Random Baichuan2 13B0K / 0.1 GB664610
Baichuan2 13B Chat0K / 27.8 GB6369424
Baichuan 13B Chat0K / 26.5 GB3356631
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Baichuan2-13B-Chat-GPTQ.

Rank the Baichuan2 13B Chat GPTQ Capabilities

๐Ÿ†˜ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! ๐ŸŒŸ

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  

What open-source LLMs or SLMs are you in search of? 46792 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227