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

ShapeLLM 13B General V1.0 by qizekun

 »  All LLMs  »  qizekun  »  ShapeLLM 13B General V1.0   URL Share it on

  55   
  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_13B_general_v1.0 

ShapeLLM 13B General V1.0 Benchmarks

LLME Score: 0.14077
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
ShapeLLM 13B General V1.0 (qizekun/ShapeLLM_13B_general_v1.0)
🌟 Advertise your project 🚀

ShapeLLM 13B General V1.0 Parameters and Internals

Model Type 
3D Object Understanding, Embodied Interaction
Use Cases 
Areas:
Research, Commercial Applications
Applications:
3D Object Understanding, Embodied Interaction
Additional Notes 
Utilizes the Large version of ReCon++ as the point encoder.
Supported Languages 
en (High)
Training Details 
Data Sources:
cap3d_objaverse_785k.json, cap3d_objaverse_sft_45k.json, gapartnet_sft_27k_openai.json, gapartnet_pcs
Methodology:
Two-stage training: 1) Fine-tuning projector for semantic alignment, 2) full fine-tuning using Instruction Following data.
Training Time:
14 hours on 8x A100 (80G) for ShapeLLM-13B; 7 hours for ShapeLLM-7B.
Hardware Used:
8x A100 (80G)
Model Architecture:
Consistent with LLaVA
Input Output 
Accepted Modalities:
3D Point Clouds
LLM NameShapeLLM 13B General V1.0
Repository 🤗https://huggingface.co/qizekun/ShapeLLM_13B_general_v1.0 
Model Size13b
Required VRAM27.4 GB
Updated2025-09-23
Maintainerqizekun
Model Typellava
Model Files  9.9 GB: 1-of-3   9.9 GB: 2-of-3   7.6 GB: 3-of-3   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 13B General V1.0

Best Alternatives
Context / RAM
Downloads
Likes
Llava V1.5 13B4K / 26 GB92564514
Llava V1.6 Vicuna 13B4K / 26.7 GB1693758
Evalalign V1.0 13B4K / 26.7 GB61
Table Llava V1.5 13B4K / 26.6 GB101
Peenoblanc 52 Llava4K / 26.7 GB60
Otterchecker4K / 26.7 GB52
Llava 13B Custom4K / 26.7 GB50
V Mllm 13B4K / 26.6 GB91
...roduct Taxonomy Llava V1.6 13B4K / 26.7 GB70
Posterllava V04K / 26.6 GB307
Note: green Score (e.g. "73.2") means that the model is better than qizekun/ShapeLLM_13B_general_v1.0.

Rank the ShapeLLM 13B 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? 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