Phi 3 Small 8K Prune6 by pszemraj

 ยป  All LLMs  ยป  pszemraj  ยป  Phi 3 Small 8K Prune6   URL Share it on

  Merged Model   Autotrain compatible Base model:finetune:microsoft/... Base model:microsoft/phi-3-sma...   Conversational   Custom code   En   Ext 8k   Instruct   Phi3small   Region:us   Safetensors   Sharded   Tensorflow

Phi 3 Small 8K Prune6 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi 3 Small 8K Prune6 (pszemraj/Phi-3-small-8k-prune6)

Phi 3 Small 8K Prune6 Parameters and Internals

Model Type 
language model, layer-pruned
Additional Notes 
This is a layer-pruned model created using mergekit. Some further pre-training is recommended for optimal performance.
Supported Languages 
en (proficient)
LLM NamePhi 3 Small 8K Prune6
Repository ๐Ÿค—https://huggingface.co/pszemraj/Phi-3-small-8k-prune6 
Base Model(s)  Phi 3 Small 8K Instruct   microsoft/Phi-3-small-8k-instruct
Merged ModelYes
Model Size6.1b
Required VRAM12.2 GB
Updated2025-02-22
Maintainerpszemraj
Model Typephi3small
Instruction-BasedYes
Model Files  4.9 GB: 1-of-3   4.8 GB: 2-of-3   2.5 GB: 3-of-3
Supported Languagesen
Context Length8k
Model ArchitecturePhi3SmallForCausalLM
Licensemit
Context Length8192
Model Max Length8192
Transformers Version4.41.1
Tokenizer ClassPhi3SmallTokenizer
Vocabulary Size100352
Torch Data Typebfloat16

Rank the Phi 3 Small 8K Prune6 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? 43470 in total.

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