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

Table Llava V1.5 7B by SpursgoZmy

 »  All LLMs  »  SpursgoZmy  »  Table Llava V1.5 7B   URL Share it on

  168   
  Arxiv:2310.03744   Arxiv:2406.08100   Autotrain compatible Dataset:liuhaotian/llava-instr... Dataset:liuhaotian/llava-pretr...   Dataset:spursgozmy/mmtab   En   Endpoints compatible   Image-text-to-text   Instruct   Llava   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/SpursgoZmy/table-llava-v1.5-7b 

Table Llava V1.5 7B Benchmarks

LLME Score: 0.21646
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Table Llava V1.5 7B (SpursgoZmy/table-llava-v1.5-7b)

Table Llava V1.5 7B Parameters and Internals

Model Type 
multimodal, chatbot, table understanding
Use Cases 
Areas:
Research, Computer Vision, NLP, AI
Primary Use Cases:
Multimodal table understanding, Question answering related to tables, Table cell description
Limitations:
Single table image input, Low input image resolution (336x336)
Supported Languages 
en (proficient)
Training Details 
Data Sources:
MMTab, LLaVA-1.5
Data Volume:
708K pre-training, 898K fine-tuning
Methodology:
Two-stage pipeline: pre-training with image-caption and table recognition data, instruction tuning with tabular and non-tabular tasks.
Model Architecture:
CLIP-ViT-L-336px as visual encoder, Vicuna-v1.5-7B as base LLM, two-layer MLP for vision-language connection.
Input Output 
Input Format:
Table image
Accepted Modalities:
image
Output Format:
text
Release Notes 
Version:
7B
Date:
January 2024
Notes:
First release for multimodal table understanding, incorporating LLaVA-v1.5 architecture.
LLM NameTable Llava V1.5 7B
Repository 🤗https://huggingface.co/SpursgoZmy/table-llava-v1.5-7b 
Model Size7b
Required VRAM14.2 GB
Updated2024-12-26
MaintainerSpursgoZmy
Model Typellava
Instruction-BasedYes
Model Files  10.0 GB: 1-of-2   4.2 GB: 2-of-2
Supported Languagesen
Model ArchitectureLlavaLlamaForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.31.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Table Llava V1.5 7B

Best Alternatives
Context / RAM
Downloads
Likes
Llava V1.6 Mistral 7B PATCHED32K / 15.1 GB238
Quilt Llava V1.5 7B4K / 14.2 GB4614
Co Instruct Llava V1.5 7B4K / 14.1 GB151
...V1.5 7b Qinstruct Preview V0.14K / 14.2 GB5134
...ct4V LLaVA Instruct Mix880k 7B4K / 14.2 GB153
Chinese LLaVA Baichuan2K / 28 GB238
KoLLaVA KoVicuna 7B2K / 27 GB18912
Llava 1.6 Gptq 8bit32K / 9.6 GB100

Rank the Table Llava V1.5 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? 40248 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 v20241217
  Support LLM Explorer