Koquality Ko Ref Llama2 7B by DILAB-HYU

 ยป  All LLMs  ยป  DILAB-HYU  ยป  Koquality Ko Ref Llama2 7B   URL Share it on

  Autotrain compatible Base model:hyunseoki/ko-ref-ll...   Dataset:dilab-hyu/koquality   Endpoints compatible   Ko   Koquality   Llama   Pytorch   Region:us   Sharded

Koquality Ko Ref Llama2 7B Parameters and Internals

LLM NameKoquality Ko Ref Llama2 7B
RepositoryOpen on ๐Ÿค— 
Base Model(s)  Ko Ref Llama2 7B   hyunseoki/ko-ref-llama2-7b
Model Size7b
Required VRAM27 GB
Model Typellama
Model Files  9.9 GB: 1-of-3   9.9 GB: 2-of-3   7.2 GB: 3-of-3
Supported Languagesko
Model ArchitectureLlamaForCausalLM
Context Length2048
Model Max Length2048
Transformers Version4.34.1
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat32
Koquality Ko Ref Llama2 7B (DILAB-HYU/koquality-ko-ref-llama2-7b)

Best Alternatives to Koquality Ko Ref Llama2 7B

Best Alternatives
HF Rank
...1M 1000000ctx AEZAKMI 3 1 17020.31024K / 13.5 GB4261
Yarn Llama 2 7B 128K0.2128K / 13.5 GB1315138
LLaMA 7B PoSE YaRN 128K0.2128K / 13.5 GB72
LLaMA 7B PoSE YaRN 96K0.296K / 13.5 GB101
LLaMA 7B PoSE Linear 96K0.296K / 27 GB71
Chat Llama2 7B 80K0.280K / 13.8 GB100
Llama2 7B 80K0.280K / 13.8 GB70
Lloma Step4000.364K / 13.5 GB4120
Lloma Step2000.364K / 13.5 GB4290
Lloma Step500.264K / 13.5 GB3540
Note: green Score (e.g. "73.2") means that the model is better than DILAB-HYU/koquality-ko-ref-llama2-7b.

Rank the Koquality Ko Ref Llama2 7B 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? 34266 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024071601