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

Imp V1.5 3B 196 by MILVLG

 »  All LLMs  »  MILVLG  »  Imp V1.5 3B 196   URL Share it on

  22   
  Arxiv:2405.12107   Autotrain compatible   Custom code Dataset:liuhaotian/llava-instr... Dataset:liuhaotian/llava-pretr...   Imp   Instruct   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/MILVLG/Imp-v1.5-3B-196 

Imp V1.5 3B 196 Benchmarks

LLME Score: 0.18709
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Imp V1.5 3B 196 (MILVLG/Imp-v1.5-3B-196)

Imp V1.5 3B 196 Parameters and Internals

Model Type 
text-generation
Additional Notes 
Model developed with reduced resolution input for improved performance on mobile devices.
Training Details 
Data Sources:
liuhaotian/LLaVA-Pretrain, liuhaotian/LLaVA-Instruct-150K
Methodology:
Reduced resolution of input image from 384 to 196 and retrained model with the same settings.
LLM NameImp V1.5 3B 196
Repository 🤗https://huggingface.co/MILVLG/Imp-v1.5-3B-196 
Model Size3b
Required VRAM6.4 GB
Updated2025-02-22
MaintainerMILVLG
Model Typeimp
Instruction-BasedYes
Model Files  1.0 GB: 1-of-7   1.0 GB: 2-of-7   1.0 GB: 3-of-7   1.0 GB: 4-of-7   1.0 GB: 5-of-7   1.0 GB: 6-of-7   0.4 GB: 7-of-7
Model ArchitectureImpForCausalLM
Licenseapache-2.0
Model Max Length3072
Transformers Version4.31.0
Tokenizer ClassCodeGenTokenizer
Beginning of Sentence Token<|endoftext|>
End of Sentence Token<|endoftext|>
Unk Token<|endoftext|>
Vocabulary Size51200
Torch Data Typefloat16
Activation Functiongelu_new
Errorsreplace

Best Alternatives to Imp V1.5 3B 196

Best Alternatives
Context / RAM
Downloads
Likes
Imp V1.5 3B Phi23K / 6.3 GB241
Imp V1 3B3K / 6.3 GB373202
Note: green Score (e.g. "73.2") means that the model is better than MILVLG/Imp-v1.5-3B-196.

Rank the Imp V1.5 3B 196 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