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 4B Phi3 by MILVLG

 »  All LLMs  »  MILVLG  »  Imp V1.5 4B Phi3   URL Share it on

  313   
  Arxiv:2405.12107   Autotrain compatible   Conversational   Custom code Dataset:liuhaotian/llava-instr... Dataset:liuhaotian/llava-pretr...   Imp phi3   Instruct   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/MILVLG/Imp-v1.5-4B-Phi3 

Imp V1.5 4B Phi3 Benchmarks

LLME Score: 0.19743
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 4B Phi3 (MILVLG/Imp-v1.5-4B-Phi3)

Imp V1.5 4B Phi3 Parameters and Internals

Model Type 
text-generation, multimodal
Training Details 
Data Sources:
liuhaotian/LLaVA-Pretrain, liuhaotian/LLaVA-Instruct-150K
Data Volume:
1M mixed dataset
Model Architecture:
Built upon Phi-3 (3.8B) and SigLIP (0.4B)
Input Output 
Input Format:
<|user|>\n\n{instruction}\n<|end|>\n<|assistant|>\n
Accepted Modalities:
text, image
LLM NameImp V1.5 4B Phi3
Repository 🤗https://huggingface.co/MILVLG/Imp-v1.5-4B-Phi3 
Model Size4b
Required VRAM8.6 GB
Updated2025-02-22
MaintainerMILVLG
Model Typeimp_phi3
Instruction-BasedYes
Model Files  1.0 GB: 1-of-9   1.0 GB: 2-of-9   1.0 GB: 3-of-9   1.0 GB: 4-of-9   1.0 GB: 5-of-9   1.0 GB: 6-of-9   1.0 GB: 7-of-9   1.0 GB: 8-of-9   0.6 GB: 9-of-9
Model ArchitectureImpPhi3ForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.36.0
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typebfloat16
Activation Functiongelu_new

Rank the Imp V1.5 4B Phi3 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