GPT2 Einstein EPFL Light by ADP-EPFL

 ยป  All LLMs  ยป  ADP-EPFL  ยป  GPT2 Einstein EPFL Light   URL Share it on

  4-bit   Autotrain compatible   En   Endpoints compatible   Gpt2   Lora   Region:us   Safetensors

GPT2 Einstein EPFL Light Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
GPT2 Einstein EPFL Light (ADP-EPFL/GPT2-Einstein-EPFL-Light)

GPT2 Einstein EPFL Light Parameters and Internals

Model Type 
text generation
Supported Languages 
en (supported)
Training Details 
Data Sources:
Llama3 Einstein dataset, EPFL type questions dataset
Methodology:
Supervised Fine Tuning (SFT) and Direct Preference Optimization (DPO)
LLM NameGPT2 Einstein EPFL Light
Repository ๐Ÿค—https://huggingface.co/ADP-EPFL/GPT2-Einstein-EPFL-Light 
Model Size431.2m
Required VRAM0.1 GB
Updated2025-02-22
MaintainerADP-EPFL
Model Files  0.1 GB   0.7 GB
Supported Languagesen
Model ArchitectureAutoModelForCausalLM
Licenseapache-2.0
Model Max Length1024
Is Biasednone
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesc_attn
LoRA Alpha128
LoRA Dropout0.05
R Param128

Rank the GPT2 Einstein EPFL Light 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