Phi 3 Mini 4K Instruct Introvert by raaec

 ยป  All LLMs  ยป  raaec  ยป  Phi 3 Mini 4K Instruct Introvert   URL Share it on

  Autotrain compatible   Code   Conversational   Custom code   Endpoints compatible   Instruct   Multilingual   Phi3   Region:us   Safetensors   Sharded   Tensorflow

Phi 3 Mini 4K Instruct Introvert Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi 3 Mini 4K Instruct Introvert (raaec/Phi-3-mini-4k-instruct-introvert)

Phi 3 Mini 4K Instruct Introvert Parameters and Internals

Model Type 
text generation
Use Cases 
Primary Use Cases:
The model is ideal for applications requiring concise, reserved responses.
Additional Notes 
The model utilizes an ablation technique with minimal data to inhibit refusal and enhance introversion without altering other behaviors, sometimes resulting in funny responses.
Supported Languages 
primary_language (multilingual), additional_languages ()
Training Details 
Methodology:
Orthogonalization is applied to ablate extroverted behaviors.
LLM NamePhi 3 Mini 4K Instruct Introvert
Repository ๐Ÿค—https://huggingface.co/raaec/Phi-3-mini-4k-instruct-introvert 
Model Size3.8b
Required VRAM7.7 GB
Updated2025-01-24
Maintainerraaec
Model Typephi3
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.7 GB: 2-of-2
Model ArchitecturePhi3ForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.41.2
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typebfloat16

Best Alternatives to Phi 3 Mini 4K Instruct Introvert

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3.5 Mini Instruct128K / 7.7 GB860851766
Phi 3 Mini 128K Instruct128K / 7.7 GB3517591626
NuExtract V1.5128K / 7.7 GB10851189
NuExtract 1.5128K / 7.7 GB21585190
Glider128K / 15.4 GB108331
Phi 3.5 Mini TitanFusion 0.1128K / 7.7 GB200
ECE EIFFEL 3Bv2128K / 7.7 GB130
Phi 3.5 Multi Ability Chatbot128K / 7.7 GB702
Samantha2.0 Phi 3.5 Mini ITA128K / 7.7 GB41810
Phi3.5 Comets 3.8B128K / 7.7 GB1210
Note: green Score (e.g. "73.2") means that the model is better than raaec/Phi-3-mini-4k-instruct-introvert.

Rank the Phi 3 Mini 4K Instruct Introvert 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? 41817 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227