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

Calme 2.2 Phi3 4B by MaziyarPanahi

 »  All LLMs  »  MaziyarPanahi  »  Calme 2.2 Phi3 4B   URL Share it on

  57   
  Autotrain compatible   Axolotl Base model:finetune:microsoft/... Base model:microsoft/phi-3-min...   Chatml   Code   Conversational   Custom code   Dpo   En   Finetuned   Instruct   Microsoft   Model-index   Phi   Phi-3   Phi3   Pytorch   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/MaziyarPanahi/calme-2.2-phi3-4b 

Calme 2.2 Phi3 4B Benchmarks

MMLU Pro: 31.27
GPQA: 9.51
MUSR: 7.7
BBH: 37.73
IFEval: 50.69 vs 88 (so35)-42.4%
MATH Lvl 5: 14.5
LLME Score: 0.24128
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
🌟 Advertise your project 🚀

Calme 2.2 Phi3 4B Parameters and Internals

LLM NameCalme 2.2 Phi3 4B
Repository 🤗https://huggingface.co/MaziyarPanahi/calme-2.2-phi3-4b 
Model CreatorMaziyarPanahi
Base Model(s)  Phi 3 Mini 4K Instruct   microsoft/Phi-3-mini-4k-instruct
Model Size4b
Required VRAM7.7 GB
Updated2025-06-09
MaintainerMaziyarPanahi
Model Typephi3
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.7 GB: 2-of-2
Supported Languagesen
Model ArchitecturePhi3ForCausalLM
Licensemit
Context Length4096
Model Max Length4096
Transformers Version4.40.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typebfloat16
Calme 2.2 Phi3 4B (MaziyarPanahi/calme-2.2-phi3-4b)

Quantized Models of the Calme 2.2 Phi3 4B

Model
Likes
Downloads
VRAM
Calme 2.2 Phi3 4B GGUF2711 GB

Best Alternatives to Calme 2.2 Phi3 4B

Best Alternatives
Context / RAM
Downloads
Likes
Calme 2.1 Phi3.5 4B128K / 7.7 GB4624
AURORAV0.3 4B128K / 7.7 GB253
Lunar 4B128K / 7.7 GB181
Phi3.5 Gutenberg 4B128K / 7.7 GB235
Calme 2.1 Phi3 4B4K / 7.7 GB401
Calme 2.3 Phi3 4B4K / 7.7 GB339
Ruphi 4B128K / 7.6 GB170
Phi 3.5 Mini Hyper128K / 7.7 GB130
...Instruct V0.3 HQQ 1bit Smashed4K / 0.9 GB240
Note: green Score (e.g. "73.2") means that the model is better than MaziyarPanahi/calme-2.2-phi3-4b.

Rank the Calme 2.2 Phi3 4B 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? 48023 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