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

Phi 3 Small 128K Instruct by microsoft

 »  All LLMs  »  microsoft  »  Phi 3 Small 128K Instruct   URL Share it on

  2887   
  Autotrain compatible   Code   Conversational   Custom code   Instruct   Multilingual   Phi3small   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/microsoft/Phi-3-small-128k-instruct 

Phi 3 Small 128K Instruct Benchmarks

MMLU Pro: 38.78
GPQA: 8.95
MUSR: 14.5
BBH: 45.63
IFEval: 63.68 vs 88 (so35)-27.6%
MATH Lvl 5: 20.26
LLME Score: 0.28747
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi 3 Small 128K Instruct (microsoft/Phi-3-small-128k-instruct)
🌟 Advertise your project 🚀

Phi 3 Small 128K Instruct Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
Commercial use, Research
Primary Use Cases:
Memory/compute constrained environments, Latency bound scenarios, Strong reasoning (especially code, math and logic)
Considerations:
Evaluate and mitigate for accuracy, safety, and fairness before using the model.
Additional Notes 
Phi-3 series models can produce unfair, unreliable, or offensive outputs.
Supported Languages 
multilingual (English primarily), other_languages (Performance varies)
Training Details 
Data Sources:
Publicly available documents, Newly created synthetic data, High quality chat format data
Data Volume:
4.8T tokens (including 10% multilingual)
Methodology:
Supervised fine-tuning (SFT) and Direct Preference Optimization (DPO)
Context Length:
128000
Training Time:
18 days
Hardware Used:
1024 H100-80G GPUs
Model Architecture:
Dense decoder-only Transformer model with alternating dense and blocksparse attentions
Responsible Ai Considerations 
Fairness:
Models are trained primarily on English text. Languages other than English and English language varieties with less representation might experience worse performance.
Mitigation Strategies:
Safety post-training was performed, though limitations may still be present.
Input Output 
Input Format:
Chat format prompts
Accepted Modalities:
text
Output Format:
Generated text
LLM NamePhi 3 Small 128K Instruct
Repository 🤗https://huggingface.co/microsoft/Phi-3-small-128k-instruct 
Model Size7.4b
Required VRAM14.8 GB
Updated2025-10-14
Maintainermicrosoft
Model Typephi3small
Instruction-BasedYes
Model Files  4.8 GB: 1-of-4   4.8 GB: 2-of-4   4.8 GB: 3-of-4   0.4 GB: 4-of-4
Model ArchitecturePhi3SmallForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.38.1
Tokenizer ClassPhi3SmallTokenizer
Padding Token<|endoftext|>
Vocabulary Size100352
Torch Data Typebfloat16

Best Alternatives to Phi 3 Small 128K Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3 Small 128K Instruct128K / 14.8 GB60
Phi 3 Small 8K Instruct8K / 14.8 GB4432168
Phi 3 Interact8K / 14.8 GB50
...hi 3 Small 8K Instruct Handler8K / 14.8 GB50
Note: green Score (e.g. "73.2") means that the model is better than microsoft/Phi-3-small-128k-instruct.

Rank the Phi 3 Small 128K Instruct 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