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 FP8 by neuralmagic

 »  All LLMs  »  neuralmagic  »  Phi 3 Mini 128K Instruct FP8   URL Share it on

  456   
  Autotrain compatible   Compressed-tensors   Conversational   Custom code   Endpoints compatible   Fp8   Instruct   Phi3   Region:us   Safetensors   Vllm
Model Card on HF 🤗: https://huggingface.co/neuralmagic/Phi-3-mini-128k-instruct-FP8 

Phi 3 Mini 128K Instruct FP8 Benchmarks

LLME Score: 0.20921
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 FP8 (neuralmagic/Phi-3-mini-128k-instruct-FP8)

Phi 3 Mini 128K Instruct FP8 Parameters and Internals

Model Type 
Text generation
Additional Notes 
The model reduces GPU memory requirements by approximately 50% using FP8 quantization. The quantization process was performed with AutoFP8 and LLM Compressor.
Supported Languages 
English (Proficient)
Training Details 
Data Sources:
UltraChat
Methodology:
The model uses symmetric per-tensor quantization mapping FP8 representations.
Context Length:
4096
Model Architecture:
Transformer with FP8 quantization for weights and activations
Input Output 
Input Format:
Text
Accepted Modalities:
Text
Output Format:
Text
Performance Tips:
Deployment with vLLM backend optimized for efficiency.
Release Notes 
Version:
1.1
Date:
8/11/2024
Notes:
Initial release of FP8 quantized version.
LLM NamePhi 3 Mini 128K Instruct FP8
Repository 🤗https://huggingface.co/neuralmagic/Phi-3-mini-128k-instruct-FP8 
Model Size3.8b
Required VRAM4 GB
Updated2024-11-27
Maintainerneuralmagic
Model Typephi3
Instruction-BasedYes
Model Files  4.0 GB
Model ArchitecturePhi3ForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.44.0
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typefloat16

Best Alternatives to Phi 3 Mini 128K Instruct FP8

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 neuralmagic/Phi-3-mini-128k-instruct-FP8.

Rank the Phi 3 Mini 128K Instruct FP8 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