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

ShapeLLM 7B General V1.0 by qizekun

 »  All LLMs  »  qizekun  »  ShapeLLM 7B General V1.0   URL Share it on

  245   
  Arxiv:2402.17766   Autotrain compatible   Dataset:qizekun/shapellm   En   Endpoints compatible   Llava   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/qizekun/ShapeLLM_7B_general_v1.0 

ShapeLLM 7B General V1.0 Benchmarks

LLME Score: 0.17496
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
ShapeLLM 7B General V1.0 (qizekun/ShapeLLM_7B_general_v1.0)

ShapeLLM 7B General V1.0 Parameters and Internals

Model Type 
3D Object Understanding, Multimodal Interaction
Use Cases 
Areas:
Research, Commercial applications
Primary Use Cases:
Semantic 3D Object Understanding, Visual Grounding
Limitations:
Not specified
Additional Notes 
ShapeLLM utilizes the Large version of ReCon++ as the point encoder for 3D transformations.
Supported Languages 
en (proficient)
Training Details 
Methodology:
Two-stage training approach: 1. Fine-tune the projector for semantic alignment. 2. Full fine-tuning using Instruction Following data.
Training Time:
7 hours for ShapeLLM-7B
Hardware Used:
8x A100 GPUs (80G)
LLM NameShapeLLM 7B General V1.0
Repository 🤗https://huggingface.co/qizekun/ShapeLLM_7B_general_v1.0 
Model Size7b
Required VRAM14.9 GB
Updated2025-02-22
Maintainerqizekun
Model Typellava
Model Files  10.0 GB: 1-of-2   4.9 GB: 2-of-2   0.0 GB
Supported Languagesen
Model ArchitectureLlavaLlamaForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
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 ShapeLLM 7B General V1.0

Best Alternatives
Context / RAM
Downloads
Likes
Llava Merged Finetuned 7b32K / 15.1 GB61
Llava V1.6 Mistral 7B PATCHED32K / 15.1 GB358
KoLLaVA V1.5 Synatra 7B32K / 15.1 GB2128
Llava V1.5 7B4K / 13.5 GB553813415
Llava V1.6 Vicuna 7B4K / 14.1 GB36623109
LLaVA NeXT Video 7B DPO4K / 14.2 GB1103425
Vip Llava 7B4K / 14.2 GB683757
Llava Next Vicuna 7B M34K / 14.1 GB6213
Video LLaVA 7B4K / 15 GB2413382
Table Llava V1.5 7B4K / 14.2 GB14111
Note: green Score (e.g. "73.2") means that the model is better than qizekun/ShapeLLM_7B_general_v1.0.

Rank the ShapeLLM 7B General V1.0 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? 43470 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 v20241227
  Support LLM Explorer