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

Llava V1.6 Mistral 7B PATCHED by Trelis

 »  All LLMs  »  Trelis  »  Llava V1.6 Mistral 7B PATCHED   URL Share it on

  5   
  Autotrain compatible   Conversational   Image-text-to-text   Instruct   Llava   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Trelis/llava-v1.6-mistral-7b-PATCHED 

Llava V1.6 Mistral 7B PATCHED Benchmarks

LLME Score: 0.13748
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llava V1.6 Mistral 7B PATCHED (Trelis/llava-v1.6-mistral-7b-PATCHED)
🌟 Advertise your project 🚀

Llava V1.6 Mistral 7B PATCHED Parameters and Internals

Model Type 
text generation, multimodal
Use Cases 
Primary Use Cases:
Research on large multimodal models and chatbots.
Additional Notes 
Patched version with patches from aliencaocao applied.
Training Details 
Data Sources:
558K filtered image-text pairs from LAION/CC/SBU, 158K GPT-generated multimodal instruction-following data, 500K academic-task-oriented VQA data mixture, 50K GPT-4V data mixture, 40K ShareGPT data
Model Architecture:
Transformer architecture
LLM NameLlava V1.6 Mistral 7B PATCHED
Repository 🤗https://huggingface.co/Trelis/llava-v1.6-mistral-7b-PATCHED 
Model Size7b
Required VRAM15.1 GB
Updated2025-09-23
MaintainerTrelis
Model Typellava
Instruction-BasedYes
Model Files  4.9 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   0.3 GB: 4-of-4
Model ArchitectureLlavaLlamaForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<pad>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Llava V1.6 Mistral 7B PATCHED

Best Alternatives
Context / RAM
Downloads
Likes
Table Llava V1.5 7B4K / 14.2 GB2313
Quilt Llava V1.5 7B4K / 14.2 GB16067
Co Instruct Llava V1.5 7B4K / 14.1 GB61
...V1.5 7b Qinstruct Preview V0.14K / 14.2 GB2295
...ct4V LLaVA Instruct Mix880k 7B4K / 14.2 GB53
Chinese LLaVA Baichuan2K / 28 GB219
KoLLaVA KoVicuna 7B2K / 27 GB2113
Llava 1.6 Gptq 8bit32K / 9.6 GB70
Note: green Score (e.g. "73.2") means that the model is better than Trelis/llava-v1.6-mistral-7b-PATCHED.

Rank the Llava V1.6 Mistral 7B PATCHED 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? 51544 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