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 Orange V2 by rhysjones

 »  All LLMs  »  rhysjones  »  Phi 2 Orange V2   URL Share it on

  239   
  Autotrain compatible   Conversational Dataset:argilla/ultrafeedback-...   Dataset:intel/orca dpo pairs   Dataset:ldjnr/capybara   Dataset:ldjnr/pure-dove   Dataset:ldjnr/verified-camel   Dataset:meta-math/metamathqa Dataset:migtissera/synthia-v1.... Dataset:open-orca/slimorca-ded...   Endpoints compatible   Model-index   Phi   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/rhysjones/phi-2-orange-v2 

Phi 2 Orange V2 Benchmarks

MMLU Pro: 17.03
GPQA: 1.57
MUSR: 6.97
BBH: 25.61
IFEval: 36.7 vs 88 (so35)-58.3%
ARC: 61.86 vs 96.7 (so35)-36%
HellaSwag: 76.32 vs 95.3 (gpt4)-19.9%
MMLU: 55.72 vs 88.3 (so35)-36.9%
TruthfulQA: 54.84 vs 59 (gpt4)-7.1%
WinoGrande: 75.69 vs 87.5 (gpt4)-13.5%
GSM8K: 57.62 vs 96.4 (so35)-40.2%
LLME Score: 0.23904
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi 2 Orange V2 (rhysjones/phi-2-orange-v2)

Phi 2 Orange V2 Parameters and Internals

Model Type 
text generation
Additional Notes 
The model is an improved version of the original Phi-2-Orange with an updated training process and the latest updated model from Microsoft's Phi-2.
Training Details 
Data Sources:
Open-Orca/SlimOrca-Dedup, migtissera/Synthia-v1.3, LDJnr/Verified-Camel, LDJnr/Pure-Dove, LDJnr/Capybara, meta-math/MetaMathQA, Intel/orca_dpo_pairs, argilla/ultrafeedback-binarized-preferences-cleaned
Input Output 
Input Format:
The model uses ChatML as the prompt format, and it's recommended to always prompt with a system instruction.
Output Format:
Text format, Markdown for Python outputs.
Performance Tips:
If the model's output is overly verbose, instruct it to be short and concise.
LLM NamePhi 2 Orange V2
Repository 🤗https://huggingface.co/rhysjones/phi-2-orange-v2 
Model Size2.8b
Required VRAM5.6 GB
Updated2025-02-05
Maintainerrhysjones
Model Typephi
Model Files  5.0 GB: 1-of-2   0.6 GB: 2-of-2
Model ArchitecturePhiForCausalLM
Licensemit
Context Length2048
Model Max Length2048
Transformers Version4.37.0
Tokenizer ClassCodeGenTokenizer
Padding Token<|endoftext|>
Vocabulary Size51200
Torch Data Typefloat16

Best Alternatives to Phi 2 Orange V2

Best Alternatives
Context / RAM
Downloads
Likes
MFANN3bv0.24128K / 11.1 GB50
MFANN3b128K / 11.1 GB1160
MFANN3bv1.3128K / 11.1 GB130
MFANN3bv1.1128K / 11.1 GB160
MFANN3bv0.23128K / 11.1 GB60
MFANN3b SFT128K / 5.6 GB1690
MFANN3b Rebase128K / 11.1 GB100
MFANN3bv1.2126K / 11.1 GB320
MFANN Phigments Slerp V232K / 5.6 GB1340
MFANN3bv0.2232K / 11.1 GB50
Note: green Score (e.g. "73.2") means that the model is better than rhysjones/phi-2-orange-v2.

Rank the Phi 2 Orange V2 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? 42577 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