KoLLaVA V1.5 Synatra 7B by tabtoyou

 »  All LLMs  »  tabtoyou  »  KoLLaVA V1.5 Synatra 7B   URL Share it on

KoLLaVA V1.5 Synatra 7B is an open-source language model by tabtoyou. Features: 7b LLM, VRAM: 15.1GB, Context: 32K, License: cc-by-sa-4.0, LLM Explorer Score: 0.1.

  Clip   Conversational   Endpoints compatible   Ko   Kollava   Llava   Pytorch   Region:us   Sharded   Synatra

KoLLaVA V1.5 Synatra 7B Benchmarks

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

KoLLaVA V1.5 Synatra 7B Parameters and Internals

Model Type 
multimodal
Additional Notes 
KoLLaVA combines the LLM Synatra with CLIP visual encoder and trained on a specific Korean visual-instruction dataset.
Supported Languages 
ko (Korean)
LLM NameKoLLaVA V1.5 Synatra 7B
Repository 🤗https://huggingface.co/tabtoyou/KoLLaVA-v1.5-Synatra-7b 
Model Size7b
Required VRAM15.1 GB
Updated2026-05-12
Maintainertabtoyou
Model Typellava
Model Files  9.9 GB: 1-of-2   5.2 GB: 2-of-2   0.0 GB
Supported Languagesko
Model ArchitectureLlavaLlamaForCausalLM
Licensecc-by-sa-4.0
Context Length32768
Model Max Length32768
Transformers Version4.31.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token<|im_end|>
Unk Token<unk>
Vocabulary Size32002
Torch Data Typebfloat16

Best Alternatives to KoLLaVA V1.5 Synatra 7B

Best Alternatives
Context / RAM
Downloads
Likes
Llava Merged Finetuned 7b32K / 15.1 GB41
Llava V1.6 Mistral 7B PATCHED32K / 15.1 GB178
Llava V1.5 7B4K / 13.5 GB186377550
Llava V1.6 Vicuna 7B4K / 14.1 GB30692144
Quilt Llava V1.5 7B4K / 14.2 GB386429
LLaVA NeXT Video 7B DPO4K / 14.2 GB129429
LLaVA NeXT Video 7B4K / 14.1 GB89051
MoMA Llava 7b4K / 14.2 GB78918
...va 1.5 Image Classification V34K / 23.3 GB1520
Table Llava V1.5 7B4K / 14.2 GB2713
Note: green Score (e.g. "73.2") means that the model is better than tabtoyou/KoLLaVA-v1.5-Synatra-7b.

Rank the KoLLaVA V1.5 Synatra 7B 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? 53972 in total.

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