Phi 3 Vision 128K Instruct Abliterated Alpha by failspy

 ยป  All LLMs  ยป  failspy  ยป  Phi 3 Vision 128K Instruct Abliterated Alpha   URL Share it on

  Autotrain compatible   Code   Conversational   Custom code   Instruct   Multilingual   Phi3 v   Pytorch   Region:us   Sharded   Vision

Phi 3 Vision 128K Instruct Abliterated Alpha 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 Vision 128K Instruct Abliterated Alpha (failspy/Phi-3-vision-128k-instruct-abliterated-alpha)

Phi 3 Vision 128K Instruct Abliterated Alpha Parameters and Internals

Model Type 
vision, text-generation
Additional Notes 
This model has certain weights manipulated to "inhibit" the model's ability to express refusal. It retains the behavior of the original model, except for the refusal directions which have been orthogonalized out. This is termed as the model being "abliterated", a play on words combining "ablation" and "obliterated".
LLM NamePhi 3 Vision 128K Instruct Abliterated Alpha
Repository ๐Ÿค—https://huggingface.co/failspy/Phi-3-vision-128k-instruct-abliterated-alpha 
Required VRAM8.3 GB
Updated2025-01-19
Maintainerfailspy
Model Typephi3_v
Instruction-BasedYes
Model Files  4.9 GB: 1-of-2   3.4 GB: 2-of-2
Model ArchitecturePhi3VForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.38.1
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typebfloat16

Best Alternatives to Phi 3 Vision 128K Instruct Abliterated Alpha

Best Alternatives
Context / RAM
Downloads
Likes
Phi Charts Train Test Val128K / 8.3 GB1200
...3 Vision Glaucoma Diagnosis V1128K / 8.3 GB341
...Vision 128K Instruct Onnx Cuda128K /  GB6227
... Vision 128K Instruct Onnx Cpu128K /  GB5028
...on 128K Instruct Onnx Directml128K /  GB428
...Vision 128K Instruct Quantized128K / 2.4 GB264

Rank the Phi 3 Vision 128K Instruct Abliterated Alpha 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? 41636 in total.

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