Distilgpt2 HC3 by pszemraj

 ยป  All LLMs  ยป  pszemraj  ยป  Distilgpt2 HC3   URL Share it on

Distilgpt2 HC3 is an open-source language model by pszemraj. Features: 88.2m LLM, VRAM: 0.3GB, License: apache-2.0, HF Score: 28.2, LLM Explorer Score: 0.11, Arc: 24.7, HellaSwag: 28, MMLU: 24, TruthfulQA: 42.1, WinoGrande: 50.4.

  Chatgpt Dataset:pszemraj/hc3-textgen-q...   En   Endpoints compatible   Generated from trainer   Gpt2   Hc3   Pytorch   Region:us   Safetensors
Model Card on HF ๐Ÿค—: https://huggingface.co/pszemraj/distilgpt2-HC3 

Distilgpt2 HC3 Benchmarks

Distilgpt2 HC3 (pszemraj/distilgpt2-HC3)
๐ŸŒŸ Advertise your project ๐Ÿš€

Distilgpt2 HC3 Parameters and Internals

Model Type 
text-generation
Use Cases 
Limitations:
This model only has 80M parameters and will likely not be factually accurate most of the time.
Additional Notes 
The model is a fine-tuned version of distilgpt2 on the 'chatgpt answers' column of the `Hello-SimpleAI/HC3` dataset. It achieved a loss of 1.9983 and accuracy of 0.5441 on the evaluation set.
Training Details 
Data Sources:
pszemraj/HC3-textgen-qa
LLM NameDistilgpt2 HC3
Repository ๐Ÿค—https://huggingface.co/pszemraj/distilgpt2-HC3 
Model Size88.2m
Required VRAM0.3 GB
Updated2025-12-29
Maintainerpszemraj
Model Typegpt2
Model Files  0.3 GB   0.3 GB   0.0 GB
Supported Languagesen
Model ArchitectureGPT2LMHeadModel
Licenseapache-2.0
Model Max Length1024
Transformers Version4.27.0.dev0
Tokenizer ClassGPT2Tokenizer
Vocabulary Size50257
Torch Data Typefloat32
Activation Functiongelu_new

Best Alternatives to Distilgpt2 HC3

Best Alternatives
Context / RAM
Downloads
Likes
Leo DistilGPT Medical0K / 0.4 GB161
Distilgpt20K / 0.4 GB2550840624
Distilgpt2 Emailgen V20K / 0.3 GB10135
Distilgpt2 Emailgen0K / 0.4 GB274
Distilgpt2 Fables Demo0K / 0.3 GB50
Distilgpt2 Nepali0K / 0.3 GB20307
Distilgpt2 Tiny Conversational0K / 0.3 GB475
Note: green Score (e.g. "73.2") means that the model is better than pszemraj/distilgpt2-HC3.

Rank the Distilgpt2 HC3 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? 52721 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum โ€” our secure, self-hosted AI agent for server management.
Release v20260328a