LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Kodialogpt V1 by heegyu

 Β»  All LLMs  Β»  heegyu  Β»  Kodialogpt V1   URL Share it on

  2807   
  Autotrain compatible   Endpoints compatible   Gpt2   Pytorch   Region:us
Model Card on HF πŸ€—: https://huggingface.co/heegyu/kodialogpt-v1 

Kodialogpt V1 Benchmarks

LLME Score: 0.08398
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Kodialogpt V1 (heegyu/kodialogpt-v1)

Kodialogpt V1 Parameters and Internals

Model Type 
Dialog Generation
Additional Notes 
The model was fine-tuned with various public Korean dialogue datasets to improve its conversational abilities.
Supported Languages 
Korean (Proficient)
Training Details 
Data Sources:
AIHub μ£Όμ œλ³„λŒ€ν™”, νŠΈμœ„ν„°, κ°μ •λŒ€ν™”, SNSλŒ€ν™”, ꡭ립ꡭ어원 λͺ¨λ‘μ˜ λ§λ­‰μΉ˜ μ˜¨λΌμΈλŒ€ν™”
Data Volume:
1,700,000 dialogues
Methodology:
Fine-tuning on Korean dialogue datasets
Training Time:
1 epoch
Model Architecture:
Based on skt/kogpt2-base-v2
Input Output 
Input Format:
Dialog prompts with prefixes '0 :' and '1 :'
Accepted Modalities:
text
Output Format:
Continuation of dialog
LLM NameKodialogpt V1
Repository πŸ€—https://huggingface.co/heegyu/kodialogpt-v1 
Required VRAM0.5 GB
Updated2024-12-21
Maintainerheegyu
Model Typegpt2
Model Files  0.5 GB
Model ArchitectureGPT2LMHeadModel
LicenseCC-BY-NC-SA 4.0
Transformers Version4.20.1
Tokenizer ClassGPT2Tokenizer
Vocabulary Size51200
Torch Data Typefloat32
Activation Functiongelu_new

Best Alternatives to Kodialogpt V1

Best Alternatives
Context / RAM
Downloads
Likes
My Model V20K /  GB770
Distilgpt2 Openvino0K / 0.3 GB240
My Model0K /  GB410
GPT 2 Large 115K Steps0K / 0 GB130
GPT 2 Large 51K Steps0K / 0 GB120
GPT 2 Large 40K Steps0K / 0 GB120
GPT 2 Large 32K Steps0K / 0 GB120
GPT 2 Large 20K Steps0K / 0 GB120
GPT 2 Large 43K Steps0K / 0 GB130
Math Gpt20K / 0.5 GB5320
Note: green Score (e.g. "73.2") means that the model is better than heegyu/kodialogpt-v1.

Rank the Kodialogpt V1 Capabilities

πŸ†˜ 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? 40013 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 v20241217
  Support LLM Explorer