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

Phi 2 Basic Maths by Menouar

 »  All LLMs  »  Menouar  »  Phi 2 Basic Maths   URL Share it on

  12   
  Adapter Base model:adapter:microsoft/p...   Base model:microsoft/phi-2   Dataset:gsm8k   En   Finetuned   Generated from trainer   Lora   Model-index   Peft   Pytorch   Region:us   Safetensors   Sft   Tensorboard   Trl
Model Card on HF 🤗: https://huggingface.co/Menouar/phi-2-basic-maths 

Phi 2 Basic Maths Benchmarks

ARC: 55.8 vs 96.7 (so35)-42.3%
HellaSwag: 71.15 vs 95.3 (gpt4)-25.3%
MMLU: 47.27 vs 88.3 (so35)-46.5%
TruthfulQA: 41.4 vs 59 (gpt4)-29.8%
WinoGrande: 75.3 vs 87.5 (gpt4)-13.9%
GSM8K: 30.71 vs 96.4 (so35)-68.1%
LLME Score: 0.19775
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi 2 Basic Maths (Menouar/phi-2-basic-maths)

Phi 2 Basic Maths Parameters and Internals

Model Type 
text generation
Training Details 
Data Sources:
gsm8k
Methodology:
The model was fine-tuned on specific datasets using techniques such as TRL, LoRA quantization, and Flash Attention.
LLM NamePhi 2 Basic Maths
Repository 🤗https://huggingface.co/Menouar/phi-2-basic-maths 
Base Model(s)  Phi 2   microsoft/phi-2
Required VRAM0.8 GB
Updated2024-12-26
MaintainerMenouar
Model Files  0.8 GB   0.0 GB
Supported Languagesen
Model ArchitectureAdapter
Licensemit
Model Max Length2048
Is Biasednone
Tokenizer ClassCodeGenTokenizer
Padding Token<|endoftext|>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesk_proj|dense|v_proj|fc2|fc1|q_proj
LoRA Alpha128
LoRA Dropout0.05
R Param256

Best Alternatives to Phi 2 Basic Maths

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3 Mini 4K Instruct Sa V0.10K / 0 GB90
Reflection Model0K / 0.2 GB01
SpectraMind0K / 16.1 GB702
L3.1 Spark R64 LoRA0K / 0.4 GB490
SpectraMindQ0K / 0.2 GB61
Mistral Small Fujin Qlora0K / 0.8 GB171
Zephyr Phi 1 5 Sft Qlora0K / 0 GB50
Phi Openllm Lb Test0K / 0 GB50
Ll3 C3 Lora New0K / 0 GB70
Hua V0.10K / 0 GB60
Note: green Score (e.g. "73.2") means that the model is better than Menouar/phi-2-basic-maths.

Rank the Phi 2 Basic Maths 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? 40303 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