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

Phi 3 Medium 4K Instruct Abliterated V3 by failspy

 »  All LLMs  »  failspy  »  Phi 3 Medium 4K Instruct Abliterated V3   URL Share it on

  4946   
  Autotrain compatible   Code   Conversational   Custom code   Endpoints compatible   Instruct   Multilingual   Phi3   Region:us   Safetensors   Sharded   Tensorflow

Phi 3 Medium 4K Instruct Abliterated V3 Benchmarks

MMLU Pro: 37.78
GPQA: 8.95
MUSR: 18.52
BBH: 46.73
IFEval: 63.19 vs 88 (so35)-28.2%
ARC: 65.44 vs 96.7 (so35)-32.3%
HellaSwag: 85.07 vs 95.3 (gpt4)-10.7%
MMLU: 75.52 vs 88.3 (so35)-14.5%
TruthfulQA: 49.98 vs 59 (gpt4)-15.3%
WinoGrande: 72.85 vs 87.5 (gpt4)-16.7%
GSM8K: 71.87 vs 96.4 (so35)-25.4%
MATH Lvl 5: 15.48
LLME Score: 0.36726
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Phi 3 Medium 4K Instruct Abliterated V3 Parameters and Internals

Model Type 
text-generation
Additional Notes 
Model has been orthogonalized to inhibit ability to refuse while maintaining other functionalities. It aims to have minimal changes from the original model behavioral characteristics, except for refusal.
Supported Languages 
language (multilingual)
Training Details 
Methodology:
ablation via orthogonalization to inhibit refusal
LLM NamePhi 3 Medium 4K Instruct Abliterated V3
Repository 🤗https://huggingface.co/failspy/Phi-3-medium-4k-instruct-abliterated-v3 
Model Size14b
Required VRAM28 GB
Updated2024-11-21
Maintainerfailspy
Model Typephi3
Instruction-BasedYes
Model Files  4.9 GB: 1-of-6   5.0 GB: 2-of-6   4.9 GB: 3-of-6   4.8 GB: 4-of-6   4.8 GB: 5-of-6   3.6 GB: 6-of-6
Model ArchitecturePhi3ForCausalLM
Licensemit
Context Length4096
Model Max Length4096
Transformers Version4.42.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typebfloat16
Phi 3 Medium 4K Instruct Abliterated V3 (failspy/Phi-3-medium-4k-instruct-abliterated-v3)

Best Alternatives to Phi 3 Medium 4K Instruct Abliterated V3

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3 Medium 128K Instruct128K / 28 GB40439371
...ess V2.5 Phi 3 Medium 128K 14B128K / 28 GB52933
Finetuned Phi3 Medium 128K128K / 28 GB150
Shisa V1 Phi3 14B128K / 28 GB112
Mahou 1.2 Phi 14B128K / 28 GB121
Phi 3 Medium 4K Instruct4K / 28 GB38586212
...colatine 14B Instruct DPO V1.24K / 28 GB615713
...hocolatine 14B Instruct 4K DPO4K / 28 GB33241
...colatine 14B Instruct DPO V1.14K / 28 GB160
Phi3 Translator Merged4K / 28 GB140
Note: green Score (e.g. "73.2") means that the model is better than failspy/Phi-3-medium-4k-instruct-abliterated-v3.

Rank the Phi 3 Medium 4K Instruct Abliterated V3 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? 38199 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 v20241110
  Support LLM Explorer