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

Chinese LLaVA Cllama2 by LinkSoul

 »  All LLMs  »  LinkSoul  »  Chinese LLaVA Cllama2   URL Share it on

  6   

Chinese LLaVA Cllama2 is an open-source language model by LinkSoul. Features: LLM, VRAM: 27GB, Context: 2K, License: openrail, Instruction-Based, LLM Explorer Score: 0.09.

Dataset:linksoul/chinese-llava...   En   Endpoints compatible   Instruct   Llava   Pytorch   Region:us   Sharded   Vision   Zh
Model Card on HF 🤗: https://huggingface.co/LinkSoul/Chinese-LLaVA-Cllama2 

Chinese LLaVA Cllama2 Benchmarks

LLME Score: 0.08771
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Chinese LLaVA Cllama2 (LinkSoul/Chinese-LLaVA-Cllama2)
🌟 Advertise your project 🚀

Chinese LLaVA Cllama2 Parameters and Internals

Model Type 
vision-language, dialogue
Use Cases 
Applications:
multimodal dialogue
Additional Notes 
The model is designed to support bilingual vision-text interaction and can be deployed easily following the provided instructions.
Supported Languages 
zh (Chinese), en (English)
Input Output 
Accepted Modalities:
text, image
LLM NameChinese LLaVA Cllama2
Repository 🤗https://huggingface.co/LinkSoul/Chinese-LLaVA-Cllama2 
Required VRAM27 GB
Updated2026-02-21
MaintainerLinkSoul
Model Typellava
Instruction-BasedYes
Model Files  9.9 GB: 1-of-3   9.9 GB: 2-of-3   7.2 GB: 3-of-3
Supported Languageszh en
Model ArchitectureLlavaLlamaForCausalLM
Licenseopenrail
Context Length2048
Model Max Length2048
Transformers Version4.28.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32003
Torch Data Typefloat32

Best Alternatives to Chinese LLaVA Cllama2

Best Alternatives
Context / RAM
Downloads
Likes
ConvLLaVA Sft 15364K / 14.9 GB180
ConvLLaVA Sft 7684K / 14.9 GB31
Note: green Score (e.g. "73.2") means that the model is better than LinkSoul/Chinese-LLaVA-Cllama2.

Rank the Chinese LLaVA Cllama2 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? 52392 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer