Yi Ko 6B DPO V5 by GAI-LLM

 ยป  All LLMs  ยป  GAI-LLM  ยป  Yi Ko 6B DPO V5   URL Share it on

  Autotrain compatible   Endpoints compatible   Ko   Llama   Pytorch   Region:us   Sharded
Model Card on HF ๐Ÿค—: https://huggingface.co/GAI-LLM/Yi-Ko-6B-dpo-v5 

Yi Ko 6B DPO V5 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Yi Ko 6B DPO V5 (GAI-LLM/Yi-Ko-6B-dpo-v5)

Yi Ko 6B DPO V5 Parameters and Internals

Model Type 
text generation
Supported Languages 
ko (native)
Training Details 
Data Sources:
Open Korean Dataset
Methodology:
Mixed-strategy with DPO
Hardware Used:
A100 GPU 80GB * 8
Model Architecture:
Yi-Ko-6B-dpo-v5 is an auto-regressive language model based on the LLaMA2 transformer architecture.
Input Output 
Accepted Modalities:
text
Output Format:
text
LLM NameYi Ko 6B DPO V5
Repository ๐Ÿค—https://huggingface.co/GAI-LLM/Yi-Ko-6B-dpo-v5 
Model Size6b
Required VRAM12.4 GB
Updated2024-12-21
MaintainerGAI-LLM
Model Typellama
Model Files  10.0 GB: 1-of-2   2.4 GB: 2-of-2
Supported Languagesko
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-4.0
Context Length2048
Model Max Length2048
Transformers Version4.32.0
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size78464
Torch Data Typebfloat16

Best Alternatives to Yi Ko 6B DPO V5

Best Alternatives
Context / RAM
Downloads
Likes
Yi 6B 200K195K / 12.1 GB7232173
Yi 6B 200K AEZAKMI V2195K / 12.1 GB11261
Yi 6B 200K DPO195K / 12.1 GB11900
Wukong Yi 6B 200K195K / 12.1 GB141
Barcenas 6B 200K195K / 12.1 GB12062
Yi 6B 200K Llamafied195K / 12.1 GB2111
Yi 6B 200K Llama195K / 12.1 GB185
Chatglm2 6B Port Llama32K / 12.5 GB134
Miqu 6B Truthy31K / 11.3 GB5031
Llama 3 6B V0.18K / 12.6 GB3712
Note: green Score (e.g. "73.2") means that the model is better than GAI-LLM/Yi-Ko-6B-dpo-v5.

Rank the Yi Ko 6B DPO V5 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? 40013 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217