Phi 3 Mini 128K Instruct Abliterated V3 by failspy

 ยป  All LLMs  ยป  failspy  ยป  Phi 3 Mini 128K Instruct Abliterated V3   URL Share it on

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

Phi 3 Mini 128K Instruct Abliterated V3 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 128K Instruct Abliterated V3 Parameters and Internals

Model Type
text-generation
Use Cases
Primary Use Cases:
Research, Understanding orthogonalization effects
Limitations:
Model may refuse certain tasks due to inherent limitations, despite orthogonalization.
Additional NotesThe model has had certain weights manipulated to inhibit refusal capabilities while maintaining original model behavior. Known to have quirks due to novel methodology.
Supported Languages
multilingual ()
Training Details
Methodology:Orthogonalized bfloat16 safetensor weights. Ablation method based on single direction control of refusal features.
Model Architecture:Inherits from original 70B instruct model with refusal directions orthogonalized out.
LLM NamePhi 3 Mini 128K Instruct Abliterated V3
Repository ๐Ÿค—https://huggingface.co/failspy/Phi-3-mini-128k-instruct-abliterated-v3 
Model Size3.8b
Required VRAM7.7 GB
Updated2024-11-13
Maintainerfailspy
Model Typephi3
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.7 GB: 2-of-2
Model ArchitecturePhi3ForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.42.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typebfloat16
Phi 3 Mini 128K Instruct Abliterated V3 (failspy/Phi-3-mini-128k-instruct-abliterated-v3)

Best Alternatives to Phi 3 Mini 128K Instruct Abliterated V3

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3.5 Mini Instruct128K / 7.7 GB671847622
Phi 3 Mini 128K Instruct128K / 7.7 GB6291751603
NuExtract V1.5128K / 7.7 GB10851189
ECE EIFFEL 3Bv2128K / 7.7 GB100
Flow Judge V0.1128K / 7.7 GB111544
Phi 3.5 Mini ITA128K / 7.7 GB781010
Borea Phi 3.5 Mini Instruct Jp128K / 7.7 GB5669
Phi 3.5 Mini TitanFusion 0.1128K / 7.7 GB880
....5 Mini 3.8B ArliAI RPMax V1.1128K / 7.7 GB1198
Borea Phi 3.5 Mini Instruct Jp128K / 7.7 GB2025
Note: green Score (e.g. "73.2") means that the model is better than failspy/Phi-3-mini-128k-instruct-abliterated-v3.

Rank the Phi 3 Mini 128K Instruct Abliterated V3 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? 37901 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110