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 Mini 128K Instruct 4 Endpoints by dordonezc

 »  All LLMs  »  dordonezc  »  Phi 3 Mini 128K Instruct 4 Endpoints   URL Share it on

  115   
  Autotrain compatible   Code   Conversational   Custom code   En   Endpoints compatible   Instruct   Phi3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/dordonezc/Phi-3-mini-128k-instruct-4-endpoints 

Phi 3 Mini 128K Instruct 4 Endpoints Benchmarks

LLME Score: 0.19836
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi 3 Mini 128K Instruct 4 Endpoints (dordonezc/Phi-3-mini-128k-instruct-4-endpoints)

Phi 3 Mini 128K Instruct 4 Endpoints Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
commercial, research
Applications:
Memory/compute constrained environments, Latency bound scenarios, Strong reasoning tasks like code, math and logic
Primary Use Cases:
language and multimodal research, generative AI-powered features
Limitations:
not specifically evaluated for all downstream purposes, performance varies across different modalities
Considerations:
Developers should apply debiasing and further mitigate for accuracy, safety, and fairness.
Supported Languages 
languages_supported (en), proficiency_levels ()
Training Details 
Data Sources:
Publicly available documents filtered for quality, high-quality educational data, code
Data Volume:
3.3T tokens
Methodology:
Supervised fine-tuning (SFT) and Direct Preference Optimization (DPO)
Context Length:
128000
Training Time:
7 days
Hardware Used:
512 H100-80G
Model Architecture:
3.8B parameter dense decoder-only Transformer model
Safety Evaluation 
Methodologies:
Supervised fine-tuning (SFT), Direct Preference Optimization (DPO)
Findings:
Can potentially behave unfairly or offend, Possibility of generating nonsensical content, Quality of Service may vary based on language variety
Risk Categories:
misinformation, stereotype perpetuation
Ethical Considerations:
Developers must adhere to responsible AI practices and ensure compliance with laws and regulations.
Responsible Ai Considerations 
Fairness:
Models may under/over-represent groups and decisions on use-cases should be sensitive to model limitations.
Transparency:
Detailed transparency related to the training and evaluation process is provided.
Accountability:
Developers are responsible for ensuring fair and compliant use.
Mitigation Strategies:
Supervised fine-tuning and direct preference optimizations are used to align with human preferences and safety guidelines.
Input Output 
Input Format:
Chat format. E.g. <|user|>Question<|end|><|assistant|>...
Accepted Modalities:
text
Output Format:
Generated text in response to inputs
LLM NamePhi 3 Mini 128K Instruct 4 Endpoints
Repository 🤗https://huggingface.co/dordonezc/Phi-3-mini-128k-instruct-4-endpoints 
Model Size3.8b
Required VRAM7.7 GB
Updated2025-02-22
Maintainerdordonezc
Model Typephi3
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.7 GB: 2-of-2
Supported Languagesen
Model ArchitecturePhi3ForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.39.3
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typebfloat16

Best Alternatives to Phi 3 Mini 128K Instruct 4 Endpoints

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3.5 Mini Instruct128K / 7.7 GB721615819
Phi 3 Mini 128K Instruct128K / 7.7 GB1741761636
NuExtract 1.5128K / 7.7 GB115378198
NuExtract V1.5128K / 7.7 GB10851189
Phi 3.5 Mini TitanFusion 0.1128K / 7.7 GB1650
Glider128K / 15.4 GB150436
Saka 3.8B128K / 7.7 GB3091
ECE EIFFEL 3Bv2128K / 7.7 GB100
Samantha2.0 Phi 3.5 Mini ITA128K / 7.7 GB41210
Artemide 3.5128K / 7.7 GB74532
Note: green Score (e.g. "73.2") means that the model is better than dordonezc/Phi-3-mini-128k-instruct-4-endpoints.

Rank the Phi 3 Mini 128K Instruct 4 Endpoints 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? 43470 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 v20241227
  Support LLM Explorer