Phi3 Hallucination Judge Merge by grounded-ai

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

  Arxiv:2305.11747   Autotrain compatible   Conversational   Custom code   Endpoints compatible   Instruct   Phi3   Region:us   Safetensors   Sharded   Tensorflow

Phi3 Hallucination 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 Hallucination Judge Merge (grounded-ai/phi3-hallucination-judge-merge)

Phi3 Hallucination Judge Merge Parameters and Internals

Training Details 
Data Sources:
arize/phoenix
Input Output 
Input Format:
Expected input format is a structured message containing a reference, a query, and a model response for hallucination evaluation.
Output Format:
The output is a binary 'yes' or 'no' indicating whether a hallucination is detected.
Performance Tips:
Improve performance by fine-tuning the prompting strategy as provided.
LLM NamePhi3 Hallucination Judge Merge
Repository ๐Ÿค—https://huggingface.co/grounded-ai/phi3-hallucination-judge-merge 
Model Size3.8b
Required VRAM7.7 GB
Updated2025-02-18
Maintainergrounded-ai
Model Typephi3
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.7 GB: 2-of-2
Model ArchitecturePhi3ForCausalLM
Licensemit
Context Length4096
Model Max Length4096
Transformers Version4.41.2
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typebfloat16

Best Alternatives to Phi3 Hallucination Judge Merge

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3.5 Mini Instruct128K / 7.7 GB867437809
Phi 3 Mini 128K Instruct128K / 7.7 GB1916751634
NuExtract 1.5128K / 7.7 GB115629196
NuExtract V1.5128K / 7.7 GB10851189
Phi 3.5 Mini TitanFusion 0.1128K / 7.7 GB1570
Glider128K / 15.4 GB129736
Saka 3.8B128K / 7.7 GB2981
ECE EIFFEL 3Bv2128K / 7.7 GB100
Samantha2.0 Phi 3.5 Mini ITA128K / 7.7 GB41320
Artemide 3.5128K / 7.7 GB77932
Note: green Score (e.g. "73.2") means that the model is better than grounded-ai/phi3-hallucination-judge-merge.

Rank the Phi3 Hallucination 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? 43267 in total.

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