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

Flow Judge V0.1 by flowaicom

 »  All LLMs  »  flowaicom  »  Flow Judge V0.1   URL Share it on

  379   
  Autotrain compatible Base model:finetune:microsoft/... Base model:microsoft/phi-3.5-m...   Conversational   Custom code Dataset:flowaicom/flow-judge-v... Dataset:flowaicom/flow-judge-v... Dataset:flowaicom/flow-judge-v...   En   Endpoints compatible   Evaluation   Instruct   Lm-judge   Phi3   Region:us   Safetensors   Sharded   Tensorflow

Flow Judge V0.1 Benchmarks

LLME Score: 0.28635
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Flow Judge V0.1 Parameters and Internals

Model Type 
text-generation
Use Cases 
Primary Use Cases:
Customizable evaluations for LLM systems using specific rubrics., Scoring scales offering binary, 3-point, and 5-point Likert scales for evaluation.
Limitations:
Multilingual capability not evaluated., Handling of long-context or structured input not addressed., Limited in specialized domains such as arithmetic and coding evaluations., Struggles with domain-specific knowledge outside training scope.
Training Details 
Methodology:
Supervised Fine-Tuning (SFT) with RSLoRa.
Context Length:
8192
Model Architecture:
Phi-3.5-mini architecture, customized and fine-tuned for evaluative tasks
Input Output 
Input Format:
Specific prompt structures with evaluation criteria, rubrics, and task outputs
Accepted Modalities:
text
Output Format:
Structured evaluation with detailed feedback
LLM NameFlow Judge V0.1
Repository 🤗https://huggingface.co/flowaicom/Flow-Judge-v0.1 
Base Model(s)  microsoft/Phi-3.5-mini-instruct   microsoft/Phi-3.5-mini-instruct
Model Size3.8b
Required VRAM7.7 GB
Updated2024-11-21
Maintainerflowaicom
Model Typephi3
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.7 GB: 2-of-2
Supported Languagesen
Model ArchitecturePhi3ForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.44.2
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typebfloat16
Flow Judge V0.1 (flowaicom/Flow-Judge-v0.1)

Best Alternatives to Flow Judge V0.1

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3.5 Mini Instruct128K / 7.7 GB651009640
Phi 3 Mini 128K Instruct128K / 7.7 GB7358311605
NuExtract 1.5128K / 7.7 GB107204113
NuExtract V1.5128K / 7.7 GB10851189
ECE EIFFEL 3Bv2128K / 7.7 GB50
Phi 3.5 Mini ITA128K / 7.7 GB788510
Borea Phi 3.5 Mini Instruct Jp128K / 7.7 GB5299
Phi 3.5 Mini TitanFusion 0.1128K / 7.7 GB290
Borea Phi 3.5 Mini Instruct Jp128K / 7.7 GB2025
....5 Mini 3.8B ArliAI RPMax V1.1128K / 7.7 GB258
Note: green Score (e.g. "73.2") means that the model is better than flowaicom/Flow-Judge-v0.1.

Rank the Flow Judge V0.1 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? 38149 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