Phi3 Toxicity Judge Merge by grounded-ai

 ยป  All LLMs  ยป  grounded-ai  ยป  Phi3 Toxicity Judge Merge   URL Share it on

  Autotrain compatible Base model:finetune:microsoft/... Base model:microsoft/phi-3-min...   Conversational   Custom code   Endpoints compatible   Generated from trainer   Instruct   Phi3   Region:us   Safetensors   Sft   Sharded   Tensorflow   Trl

Phi3 Toxicity Judge Merge Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi3 Toxicity Judge Merge (grounded-ai/phi3-toxicity-judge-merge)

Phi3 Toxicity Judge Merge Parameters and Internals

Model Type 
toxicity classification
Input Output 
Input Format:
Formatted prompt indicating text to analyze as toxic or non-toxic with justification.
Accepted Modalities:
text
Output Format:
Single word classification of 'toxic' or 'non-toxic', followed by reasoning.
Performance Tips:
Use recommended prompting strategy for best results.
LLM NamePhi3 Toxicity Judge Merge
Repository ๐Ÿค—https://huggingface.co/grounded-ai/phi3-toxicity-judge-merge 
Base Model(s)  Phi 3 Mini 4K Instruct   microsoft/Phi-3-mini-4k-instruct
Model Size3.8b
Required VRAM15.4 GB
Updated2024-12-21
Maintainergrounded-ai
Model Typephi3
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   5.0 GB: 3-of-4   0.4 GB: 4-of-4
Model ArchitecturePhi3ForCausalLM
Licensemit
Context Length4096
Model Max Length4096
Transformers Version4.41.1
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typefloat32

Best Alternatives to Phi3 Toxicity Judge Merge

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3.5 Mini Instruct128K / 7.7 GB605206703
Phi 3 Mini 128K Instruct128K / 7.7 GB8279851615
NuExtract V1.5128K / 7.7 GB10851189
NuExtract 1.5128K / 7.7 GB11145174
Phi 3.5 Mini TitanFusion 0.1128K / 7.7 GB250
ECE EIFFEL 3Bv2128K / 7.7 GB120
Artemide 3.5128K / 7.7 GB83392
Phi 3.5 Mini ITA128K / 7.7 GB872711
Flow Judge V0.1128K / 7.7 GB26846
Borea Phi 3.5 Mini Instruct Jp128K / 7.7 GB37310
Note: green Score (e.g. "73.2") means that the model is better than grounded-ai/phi3-toxicity-judge-merge.

Rank the Phi3 Toxicity Judge Merge 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? 40013 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217