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 4K Instruct IMat GGUF by qwp4w3hyb

 »  All LLMs  »  qwp4w3hyb  »  Phi 3 Mini 4K Instruct IMat GGUF   URL Share it on

  304   
  Autotrain compatible Base model:microsoft/phi-3-min... Base model:quantized:microsoft...   Code   Conversational   Custom code   En   Endpoints compatible   Gguf   Imatrix   Importance matrix   Instruct   Microsoft   Phi   Phi-3   Phi3   Q4   Quantized   Region:us

Phi 3 Mini 4K Instruct IMat GGUF Benchmarks

LLME Score: 0.2078
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 4K Instruct IMat GGUF Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
commercial, research
Applications:
memory/compute constrained environments, latency bound scenarios, strong reasoning capabilities such as code, math, and logic
Primary Use Cases:
language and multimodal models research, generative AI powered features
Limitations:
models are not specifically designed or evaluated for all downstream purposes
Considerations:
Developers should evaluate accuracy, safety, and fairness before using in a specific downstream use case.
Supported Languages 
en (native)
Training Details 
Data Sources:
publicly available documents, selected high-quality educational data, newly created synthetic data, high quality chat format supervised data
Data Volume:
3.3 trillion tokens
Methodology:
Supervised fine-tuning (SFT) and Direct Preference Optimization (DPO)
Context Length:
4000
Training Time:
7 days
Hardware Used:
512 H100-80G GPUs
Model Architecture:
Dense decoder-only Transformer model
Responsible Ai Considerations 
Fairness:
Models can over- or under-represent groups of people and may reinforce negative stereotypes.
Transparency:
Developers should apply responsible AI best practices.
Accountability:
Developers are responsible for ensuring compliance with relevant laws and regulations.
Mitigation Strategies:
Use available safety classifiers or custom solutions appropriate for the use case.
Input Output 
Input Format:
Text using chat format
Accepted Modalities:
text
Output Format:
Generated text in response to input
LLM NamePhi 3 Mini 4K Instruct IMat GGUF
Repository 🤗https://huggingface.co/qwp4w3hyb/Phi-3-mini-4k-instruct-iMat-GGUF 
Base Model(s)  Phi 3 Mini 4K Instruct   microsoft/Phi-3-mini-4k-instruct
Required VRAM0.8 GB
Updated2024-11-21
Maintainerqwp4w3hyb
Model Typephi3
Instruction-BasedYes
Model Files  7.6 GB   7.6 GB   15.3 GB   0.8 GB   1.3 GB   1.2 GB   1.1 GB   1.0 GB   1.9 GB   1.7 GB   1.6 GB   1.5 GB   2.2 GB   2.1 GB   2.2 GB   2.4 GB   2.2 GB   2.8 GB   2.6 GB   3.1 GB   4.1 GB
Supported Languagesen
GGUF QuantizationYes
Quantization Typegguf|q4|q4_k|q5_k
Model ArchitecturePhi3ForCausalLM
Licensemit
Context Length4096
Model Max Length4096
Transformers Version4.39.3
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typebfloat16
Phi 3 Mini 4K Instruct IMat GGUF (qwp4w3hyb/Phi-3-mini-4k-instruct-iMat-GGUF)

Best Alternatives to Phi 3 Mini 4K Instruct IMat GGUF

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3 Mini 128K Instruct GGUF128K / 1.4 GB3012
...hi 3 Medium 128K Instruct GGUF128K / 5.1 GB1882
Phi 3 Mini 128K Instruct GGUF128K / 1.4 GB1051
...hi 3 Medium 128K Instruct GGUF128K / 5.1 GB710
...i 3 Mini 4K Instruct.Q4 0.gguf128K / 2.2 GB1882
Phi 3 Mini 4K Instruct GGUF4K / 1.4 GB5943
Phi 3 Medium 4K Instruct GGUF4K / 5.1 GB1120
Phi 3 Medium 4K Instruct GGUF4K / 5.1 GB1010
Phi 3 Mini 128K Instruct Gguf0K / 1.4 GB741
...m 128K Instruct 8.0bpw H8 EXL2128K / 13.4 GB134
Note: green Score (e.g. "73.2") means that the model is better than qwp4w3hyb/Phi-3-mini-4k-instruct-iMat-GGUF.

Rank the Phi 3 Mini 4K Instruct IMat GGUF 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