Orpo Phi3 3B 128K by Muhammad2003

 ยป  All LLMs  ยป  Muhammad2003  ยป  Orpo Phi3 3B 128K   URL Share it on

  Autotrain compatible Base model:finetune:microsoft/... Base model:microsoft/phi-3-min...   Conversational   Custom code Dataset:mlabonne/orpo-dpo-mix-...   En   Endpoints compatible   Instruct   Orpo   Phi 3   Phi3   Region:us   Safetensors   Sharded   Tensorflow

Orpo Phi3 3B 128K Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
๐ŸŒŸ Advertise your project ๐Ÿš€

Orpo Phi3 3B 128K Parameters and Internals

Model Type 
text generation
Supported Languages 
en (proficient)
Training Details 
Data Sources:
mlabonne/orpo-dpo-mix-40k
LLM NameOrpo Phi3 3B 128K
Repository ๐Ÿค—https://huggingface.co/Muhammad2003/Orpo-Phi3-3B-128K 
Base Model(s)  Phi 3 Mini 128K Instruct   microsoft/Phi-3-mini-128k-instruct
Model Size3b
Required VRAM7.7 GB
Updated2024-12-02
MaintainerMuhammad2003
Model Typephi3
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.7 GB: 2-of-2
Supported Languagesen
Model ArchitecturePhi3ForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.41.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<|im_end|>
Vocabulary Size32013
Torch Data Typefloat16
Orpo Phi3 3B 128K (Muhammad2003/Orpo-Phi3-3B-128K)

Best Alternatives to Orpo Phi3 3B 128K

Best Alternatives
Context / RAM
Downloads
Likes
...ocolatine 3B Instruct DPO V1.2128K / 7.7 GB30518
ECE EIFFEL 3B128K / 7.7 GB60
ECE GRENELLE 3B128K / 7.7 GB590
Phi3 3B Ultrachat Svd Model128K / 7.7 GB81
...latine 3B Instruct DPO Revised4K / 7.7 GB104325
ECE PRYMMAL 3B SLERP 2 V24K / 7.7 GB140
ECE PRYMMAL 3B SLERP 2 V14K / 7.7 GB100
ECE EIFFEL 3Bv34K / 7.7 GB50
...ocolatine 3B Instruct DPO V1.04K / 7.7 GB7263
ECE PRYMMAL 3B SLERP V14K / 7.7 GB50
Note: green Score (e.g. "73.2") means that the model is better than Muhammad2003/Orpo-Phi3-3B-128K.

Rank the Orpo Phi3 3B 128K Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 38765 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124