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

Llama 3 Korean 8B AWQ by sh2orc

 »  All LLMs  »  sh2orc  »  Llama 3 Korean 8B AWQ   URL Share it on

  77   
  4-bit   Autotrain compatible   Awq   Conversational   Endpoints compatible   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/sh2orc/llama-3-korean-8b-awq 

Llama 3 Korean 8B AWQ Benchmarks

LLME Score: 0.19061
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3 Korean 8B AWQ (sh2orc/llama-3-korean-8b-awq)

Llama 3 Korean 8B AWQ Parameters and Internals

Model Type 
Foundation Model
Use Cases 
Areas:
Research, Text generation
Applications:
Ai assistant, Chatbot interactions
Primary Use Cases:
Generating responses to queries, Elaborating on user input
Supported Languages 
languages (Korean), proficiency (Native proficiency)
Training Details 
Data Sources:
Koalpaca v1.1a, korean_safe_conversation
Methodology:
Paged Attention, AWQ quantization
Input Output 
Input Format:
Tokenized input using pre-trained tokenizer
Accepted Modalities:
Text
Output Format:
Generated text
LLM NameLlama 3 Korean 8B AWQ
Repository 🤗https://huggingface.co/sh2orc/llama-3-korean-8b-awq 
Base Model(s)  Llama 3 Korean 8B   sh2orc/Llama-3-Korean-8B
Model Size8b
Required VRAM6 GB
Updated2025-02-05
Maintainersh2orc
Model Typellama
Model Files  4.8 GB: 1-of-2   1.2 GB: 2-of-2
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.40.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size145088
Torch Data Typefloat16

Best Alternatives to Llama 3 Korean 8B AWQ

Best Alternatives
Context / RAM
Downloads
Likes
...8B Instruct Gradient 1048K AWQ1024K / 5.8 GB780
...radient 1048K AWQ 4bit Smashed1024K / 5.8 GB51
...Instruct 262K AWQ 4bit Smashed256K / 5.8 GB74
...ta Llama 3 8B Instruct 64K AWQ64K / 5.8 GB770
... Instruct 8B 32K V0.1 4bit AWQ64K / 5.8 GB820
Llama 3 8B Instruct AWQ8K / 5.8 GB1089722
Llama 3 ELYZA JP 8B AWQ8K / 5.8 GB29983
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB8945
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB760
...eta Llama 3 8B Instruct Hf AWQ8K / 5.8 GB5388
Note: green Score (e.g. "73.2") means that the model is better than sh2orc/llama-3-korean-8b-awq.

Rank the Llama 3 Korean 8B AWQ 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? 42625 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 v20241227
  Support LLM Explorer