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

EEVE Korean 10.8B V1.0 16K by maywell

 »  All LLMs  »  maywell  »  EEVE Korean 10.8B V1.0 16K   URL Share it on

  29   
  Arxiv:2402.14714   Autotrain compatible Base model:finetune:yanolja/ee... Base model:yanolja/eeve-korean...   Conversational   Endpoints compatible   Llama   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/maywell/EEVE-Korean-10.8B-v1.0-16k 

EEVE Korean 10.8B V1.0 16K Benchmarks

LLME Score: 0.18866
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
EEVE Korean 10.8B V1.0 16K (maywell/EEVE-Korean-10.8B-v1.0-16k)

EEVE Korean 10.8B V1.0 16K Parameters and Internals

Model Type 
Language Model
Use Cases 
Areas:
Korean language tasks
Limitations:
Not fine-tuned with instruction-based training.
Considerations:
Further training advised for specific applications.
Supported Languages 
Korean (Advanced)
Training Details 
Data Sources:
Korean web-crawled datasets
Data Volume:
100GB Korean corpus
Methodology:
Subword-based embedding with a seven-stage training process involving parameter freezing and vocabulary expansion.
Model Architecture:
Vocabulary-extended version using subword embedding and parameter freezing.
LLM NameEEVE Korean 10.8B V1.0 16K
Repository 🤗https://huggingface.co/maywell/EEVE-Korean-10.8B-v1.0-16k 
Base Model(s)  yanolja/EEVE-Korean-10.8B-v1.0   yanolja/EEVE-Korean-10.8B-v1.0
Model Size10.8b
Required VRAM21.6 GB
Updated2024-12-26
Maintainermaywell
Model Typellama
Model Files  10.0 GB: 1-of-3   10.0 GB: 2-of-3   1.6 GB: 3-of-3
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length16384
Model Max Length16384
Transformers Version4.34.0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size40960
Torch Data Typefloat16

Best Alternatives to EEVE Korean 10.8B V1.0 16K

Best Alternatives
Context / RAM
Downloads
Likes
...Korean Instruct 10.8B V1.0 32K32K / 21.6 GB7510
...EVE Korean Instruct 10.8B V1.04K / 21.6 GB22493137
...Judgment Transducer 10.8B V2.04K / 21.6 GB2950
EEVE Korean 10.8B RAFT4K / 43.2 GB47670
T3Q LLM1 CV V1.04K / 21.6 GB92100
T3Q LLM1 CV V2.04K / 21.6 GB47710
EEVE Ver 4.1 Sft4K / 21.6 GB47670
T3Q LLM Sft1.0 Dpo1.04K / 21.6 GB47720
T3Q LLM Solar10.8 Sft V1.04K / 21.6 GB47690
AlgograpV44K / 43.2 GB47640
Note: green Score (e.g. "73.2") means that the model is better than maywell/EEVE-Korean-10.8B-v1.0-16k.

Rank the EEVE Korean 10.8B V1.0 16K Capabilities

🆘 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? 40248 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