Llama3 Ko 4bit by vessl

 ยป  All LLMs  ยป  vessl  ยป  Llama3 Ko 4bit   URL Share it on

  Merged Model   Arxiv:1910.09700   4-bit   4bit   Autotrain compatible   Bitsandbytes   Endpoints compatible   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/vessl/llama3-ko-4bit 

Llama3 Ko 4bit Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
๐ŸŒŸ Advertise your project ๐Ÿš€

Llama3 Ko 4bit Parameters and Internals

LLM NameLlama3 Ko 4bit
Repository ๐Ÿค—https://huggingface.co/vessl/llama3-ko-4bit 
Merged ModelYes
Model Size4.7b
Required VRAM5.8 GB
Updated2025-06-09
Maintainervessl
Model Typellama
Model Files  4.7 GB: 1-of-2   1.1 GB: 2-of-2
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.38.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128256
Torch Data Typefloat16
Llama3 Ko 4bit (vessl/llama3-ko-4bit)

Best Alternatives to Llama3 Ko 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Llama3.1 Merged128K / 5.8 GB280
EPFL TA Meister 4bit8K / 5.8 GB180
Book 4bitV58K / 5.8 GB150
Book 4bit8K / 5.8 GB130
Tenebra PreAlpha 128g 4BIT2K / 17.6 GB180
...loth Llama3.1 Instruct Bnb4bit128K / 5.8 GB60
Airoboros C34B 3.1.2 GPTQ16K / 17.7 GB111
Airoboros C34b 2.2.1 GPTQ16K / 17.7 GB332
Airoboros C34B 2.2 GPTQ16K / 17.7 GB111
Airoboros C34B 2.1 GPTQ16K / 17.7 GB2512
Note: green Score (e.g. "73.2") means that the model is better than vessl/llama3-ko-4bit.

Rank the Llama3 Ko 4bit 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? 48046 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124