Urllm Ko En 2.7B by URP

 ยป  All LLMs  ยป  URP  ยป  Urllm Ko En 2.7B   URL Share it on

  Merged Model   Autotrain compatible   En   Endpoints compatible   Ko   Llama   Llama-2-ko-en   Llama2   Meta   Pytorch   Region:us   Sharded   Sheared llama
Model Card on HF ๐Ÿค—: https://huggingface.co/URP/urllm-ko_en-2.7b 

Urllm Ko En 2.7B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Urllm Ko En 2.7B (URP/urllm-ko_en-2.7b)

Urllm Ko En 2.7B Parameters and Internals

Model Type 
auto-regressive, text generation
Additional Notes 
Vocab Expansion of 51385.
Supported Languages 
Korean (Advanced), English (Advanced)
Training Details 
Data Sources:
Modu Corpus, Korean Wikipedia, Kaggle English News
Data Volume:
approximately total 36GB
Model Architecture:
optimized transformer
LLM NameUrllm Ko En 2.7B
Repository ๐Ÿค—https://huggingface.co/URP/urllm-ko_en-2.7b 
Merged ModelYes
Model Size2.7b
Required VRAM11.2 GB
Updated2025-02-22
MaintainerURP
Model Typellama
Model Files  10.0 GB: 1-of-2   1.2 GB: 2-of-2
Supported Languagesko en
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-4.0
Context Length4096
Model Max Length4096
Transformers Version4.32.1
Tokenizer ClassLlamaTokenizer
Vocabulary Size51385
Torch Data Typefloat32

Best Alternatives to Urllm Ko En 2.7B

Best Alternatives
Context / RAM
Downloads
Likes
Sheared LLaMA 2.7B4K / 10.8 GB319860
Shearedplats 2.7B V24K / 5.7 GB33252
Dopeyshearedplats 2.7B V14K / 5.7 GB19632
Llama Final4K / 5.5 GB610
DPO VinaLlama Completed4K / 5.6 GB550
...redplats 2.7B V2 Instruct V0.14K / 5.4 GB1843
...heared Llama 2.7B Deita 6K Sft4K / 5.4 GB1421
Shearedplats 2.7B V14K / 5.7 GB20462
Sheared LLaMA 2.7B Weblinx4K / 5.4 GB182
Vinallama 2.7B4K / 5.5 GB66413
Note: green Score (e.g. "73.2") means that the model is better than URP/urllm-ko_en-2.7b.

Rank the Urllm Ko En 2.7B 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? 43470 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227