LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Blossom V3.1 Baichuan2 13B by Azure99

 »  All LLMs  »  Azure99  »  Blossom V3.1 Baichuan2 13B   URL Share it on

  5   
  Baichuan   Custom code Dataset:azure99/blossom-chat-v... Dataset:azure99/blossom-math-v... Dataset:azure99/blossom-orca-v... Dataset:azure99/blossom-wizard...   En   Endpoints compatible   Feature-extraction   Pytorch   Region:us   Sharded   Zh
Model Card on HF 🤗: https://huggingface.co/Azure99/blossom-v3_1-baichuan2-13b 

Blossom V3.1 Baichuan2 13B Benchmarks

LLME Score: 0.1223
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Blossom V3.1 Baichuan2 13B (Azure99/blossom-v3_1-baichuan2-13b)
🌟 Advertise your project 🚀

Blossom V3.1 Baichuan2 13B Parameters and Internals

Model Type 
text generation
Additional Notes 
Trained on a high-quality mix of Chinese and English datasets for enhanced general and contextual comprehension abilities.
Supported Languages 
zh (high), en (high)
Training Details 
Data Sources:
Azure99/blossom-chat-v1, Azure99/blossom-math-v2, Azure99/blossom-wizard-v1, Azure99/blossom-orca-v1
Methodology:
Instruction fine-tuning in two stages: - Stage 1: 100K Wizard and 100K Orca single-turn instruction datasets for 1 epoch. - Stage 2: 2K Blossom math reasoning dataset, 50K Blossom chat multi-turn dialogue dataset, and 1% random sample from stage 1 data for 3 epochs.
Input Output 
Input Format:
Conversation continuation format for both single-turn and multi-turn dialogues.
Accepted Modalities:
text
Output Format:
Textual responses in a conversational manner.
Performance Tips:
Ensure conversation history is included with <Bot> output endings followed by </s> for continuity in multi-turn dialogues.
LLM NameBlossom V3.1 Baichuan2 13B
Repository 🤗https://huggingface.co/Azure99/blossom-v3_1-baichuan2-13b 
Model Size13b
Required VRAM27.8 GB
Updated2025-09-23
MaintainerAzure99
Model Typebaichuan
Model Files  10.0 GB: 1-of-3   9.9 GB: 2-of-3   7.9 GB: 3-of-3
Supported Languageszh en
Model ArchitectureBaichuanForCausalLM
Licenseapache-2.0
Model Max Length4096
Transformers Version4.33.2
Tokenizer ClassBaichuanTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size125696
Torch Data Typebfloat16

Best Alternatives to Blossom V3.1 Baichuan2 13B

Best Alternatives
Context / RAM
Downloads
Likes
Tiny Random Baichuan2 13B0K / 0.1 GB904960
Baichuan2 13B Chat0K / 27.8 GB5574429
Baichuan 13B Chat0K / 26.5 GB3872632
ShieldLM 13B Baichuan20K / 27.8 GB83
Baichuan2 13B Base0K / 27.8 GB165081
HuatuoGPT2 13B0K / 29.1 GB318
Buffer Baichuan2 13B Rag 4bits0K / 9.9 GB60
Buffer Baichuan2 13B Rag0K / 27.8 GB61
Baichuan 13B Base0K / 26.5 GB1104187
... Efficient Training Of LLMs V10K / 29.1 GB111
Note: green Score (e.g. "73.2") means that the model is better than Azure99/blossom-v3_1-baichuan2-13b.

Rank the Blossom V3.1 Baichuan2 13B Capabilities

🆘 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! 🌟

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? 51538 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124
  Support LLM Explorer