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 Ov Int8 by fakezeta

 »  All LLMs  »  fakezeta  »  Phi 3 Mini 128K Instruct Ov Int8   URL Share it on

  9   
  Autotrain compatible   Conversational   Custom code   Endpoints compatible   Instruct   Openvino   Phi3   Region:us
Model Card on HF 🤗: https://huggingface.co/fakezeta/Phi-3-mini-128k-instruct-ov-int8 

Phi 3 Mini 128K Instruct Ov Int8 Benchmarks

LLME Score: 0.14763
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 Ov Int8 (fakezeta/Phi-3-mini-128k-instruct-ov-int8)
🌟 Advertise your project 🚀

Phi 3 Mini 128K Instruct Ov Int8 Parameters and Internals

Model Type 
Dense decoder-only Transformer, Text generation
Use Cases 
Areas:
Research, Commercial applications
Applications:
Memory/compute constrained environments, Latency bound scenarios, Strong reasoning in code, math and logic
Primary Use Cases:
Language model building, Generative AI features
Limitations:
Limited language support outside English, Misrepresentation of groups, Inappropriate responses possible, Potential for misinformation
Considerations:
Assess outputs for context, legality and relevance of use. Utilize safety classifiers or custom solutions.
Additional Notes 
Cross-platform support via ONNX runtime for various devices.
Supported Languages 
English (primary)
Training Details 
Data Sources:
Publicly available documents, High-quality educational data, Synthetic data
Data Volume:
3.3 trillion tokens
Methodology:
Supervised fine-tuning (SFT), Direct Preference Optimization (DPO)
Context Length:
4000
Training Time:
7 days
Hardware Used:
512 H100-80G GPUs
Model Architecture:
Dense decoder-only Transformer
Safety Evaluation 
Methodologies:
Post-training supervised fine-tuning, Direct Preference Optimization
Findings:
Potential for bias in representation of groups, Possible generation of inappropriate content, Potential for misinformation
Risk Categories:
Misinformation, Bias, Inappropriate content
Ethical Considerations:
Evaluate suitability for high-risk scenarios. Ensure legality of use.
Responsible Ai Considerations 
Fairness:
Recognize the potential for unfair or biased outputs. Evaluate and mitigate these risks before using in sensitive applications.
Transparency:
Follow transparency best practices by informing users they are interacting with AI. Use known techniques to ground responses in use-case specific information.
Accountability:
Developers are responsible for compliance with relevant laws and regulations. Implement necessary safeguards in high-risk scenarios.
Mitigation Strategies:
Apply responsible AI best practices and debiasing techniques for high-stakes scenarios.
Input Output 
Input Format:
Text, chat format prompts
Accepted Modalities:
Text
Output Format:
Generated responses to input
Performance Tips:
Use few-shot prompting and ensure context is within 4K tokens.
LLM NamePhi 3 Mini 128K Instruct Ov Int8
Repository 🤗https://huggingface.co/fakezeta/Phi-3-mini-128k-instruct-ov-int8 
Required VRAM0 GB
Updated2025-09-23
Maintainerfakezeta
Model Typephi3
Instruction-BasedYes
Model Files  0.0 GB   3.8 GB   0.0 GB
Model ArchitecturePhi3ForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.41.2
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064

Best Alternatives to Phi 3 Mini 128K Instruct Ov Int8

Best Alternatives
Context / RAM
Downloads
Likes
Phi 4 Mini Instruct ONNX GQA128K /  GB134
Phi 3.5 Mini Instruct Onnx Web128K /  GB206914
Phi 3.5 Mini Instruct Onnx128K /  GB106531
Phi 3 Mini 128K Instruct Onnx128K /  GB1111191
...Medium 128K Instruct Onnx Cuda128K /  GB5023
...i 3 Mini 128K Instruct Ov Int4128K / 2 GB60
... Medium 128K Instruct Onnx Cpu128K /  GB6311
...3 Mini 128K Instruct Asym Int4128K / 2.5 GB1220
...um 128K Instruct Onnx Directml128K /  GB145
Model1128K / 0.8 GB200
Note: green Score (e.g. "73.2") means that the model is better than fakezeta/Phi-3-mini-128k-instruct-ov-int8.

Rank the Phi 3 Mini 128K Instruct Ov Int8 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? 51545 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 v20241124
  Support LLM Explorer