LLM EXPLORER 59,420 MODELS INDEXED

EEVE Korean Instruct 10.8B V1.0 by yanolja

By yanolja · 9491 downloads

EEVE Korean Instruct 10.8B V1.0 is an open-source language model by yanolja. Features: 10.8b LLM, VRAM: 21.6GB, Context: 4K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.16, Arc: 64.9, HellaSwag: 83, MMLU: 64.2, GSM8K: 50.7.

  Arxiv:2306.02707   Arxiv:2310.01377   Arxiv:2402.14714   Autotrain compatible Base model:finetune:yanolja/ee... Base model:yanolja/eeve-korean...   Conversational   Endpoints compatible   Generated from trainer   Instruct   Llama   Region:us   Safetensors   Sharded   Tensorflow

EEVE Korean Instruct 10.8B V1.0 Parameters and Internals

Model Type 
text generation
Additional Notes 
Join our Discord community for more insights.
Supported Languages 
Korean (proficient)
Training Details 
Data Sources:
Korean-translated version of Open-Orca/SlimOrca-Dedup, Korean-translated version of argilla/ultrafeedback-binarized-preferences-cleaned
Methodology:
Direct Preference Optimization (DPO)
Input Output 
Input Format:
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. Human: {prompt} Assistant:
Accepted Modalities:
text
Output Format:
Text responses
LLM NameEEVE Korean Instruct 10.8B V1.0
Repository πŸ€—https://huggingface.co/yanolja/EEVE-Korean-Instruct-10.8B-v1.0 
Base Model(s)  yanolja/EEVE-Korean-10.8B-v1.0   yanolja/EEVE-Korean-10.8B-v1.0
Model Size10.8b
Required VRAM21.6 GB
Updated2025-09-02
Maintaineryanolja
Model Typellama
Instruction-BasedYes
Model Files  4.9 GB: 1-of-5   4.9 GB: 2-of-5   5.0 GB: 3-of-5   4.9 GB: 4-of-5   1.9 GB: 5-of-5
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size40960
Torch Data Typebfloat16

Best Alternatives to EEVE Korean Instruct 10.8B V1.0

Best Alternatives
Context / RAM
Downloads
Likes
...Korean Instruct 10.8B V1.0 32K32K / 21.6 GB4010
...anoljaNEXT EEVE Instruct 10.8B4K / 21.6 GB14441166
...Judgment Transducer 10.8B V2.04K / 21.6 GB50
Hkcode Meta QA54K / 21.6 GB100
Eeve Leaderboard Inst V1.54K / 21.6 GB21570
...struct 10.8B V1.0 Empathy V0.14K / 21.6 GB70
EEVE Korean Instruct 10.8B Var4K / 21.6 GB54
EEVE 10.8 BOOK V0.14K / 21.6 GB71
AlgograpV44K / 43.2 GB80
EEVE Instruct Math 10.8B4K / 21.6 GB93