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

Phi3 4K by ehartford

 »  All LLMs  »  ehartford  »  Phi3 4K   URL Share it on

  22   
  Arxiv:1910.09700   Autotrain compatible   Conversational   Custom code   Endpoints compatible   Instruct   Phi3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/ehartford/phi3-4k 

Phi3 4K Benchmarks

ARC: 96.3 vs 96.7 (so35)-0.4%
HellaSwag: 87.5 vs 95.3 (gpt4)-8.2%
MMLU: 72.9 vs 88.3 (so35)-17.4%
GSM8K: 21.7 vs 96.4 (so35)-77.5%
OpenCompas: 59.3 vs 73.3 (gpt4)-19.1%
Exam: 77.6 vs 77.2 (gpt4)0.5%
Language: 36.1 vs 62 (gpt4)-41.8%
Knowledge: 61.6 vs 73.5 (gpt4)-16.2%
Understand: 70.8 vs 70 (gpt4)1.1%
Reasoning: 55.9 vs 74.4 (gpt4)-24.9%
LLME Score: 0.16392
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi3 4K (ehartford/phi3-4k)
🌟 Advertise your project 🚀

Phi3 4K Parameters and Internals

Additional Notes 
This model card is automatically generated as part of ongoing experimentation and is not meant for reuse. Significant information required throughout.
LLM NamePhi3 4K
Repository 🤗https://huggingface.co/ehartford/phi3-4k 
Model Size3.8b
Required VRAM7.7 GB
Updated2025-07-01
Maintainerehartford
Model Typephi3
Instruction-BasedYes
Model Files  2.0 GB: 1-of-4   1.9 GB: 2-of-4   2.0 GB: 3-of-4   1.8 GB: 4-of-4
Model ArchitecturePhi3ForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.41.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typebfloat16

Best Alternatives to Phi3 4K

Best Alternatives
Context / RAM
Downloads
Likes
Phi 4 Mini Instruct128K / 7.7 GB205786531
Phi 3.5 Mini Instruct128K / 7.7 GB258183880
Phi 3 Mini 128K Instruct128K / 7.7 GB3177571652
NuExtract V1.5128K / 7.7 GB10851189
Phi 4 Mini Instruct128K / 7.7 GB568716
NuExtract 1.5128K / 7.7 GB9113235
Phi 3.5 Mini TitanFusion 0.1128K / 7.7 GB170
ECE EIFFEL 3Bv2128K / 7.7 GB50
Glider128K / 15.4 GB176141
Phi 4 Bifrost Sol 3.8B128K / 7.7 GB381
Note: green Score (e.g. "73.2") means that the model is better than ehartford/phi3-4k.

Rank the Phi3 4K 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? 49327 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