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

Llama 2 7B Vietnamese 20K GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Llama 2 7B Vietnamese 20K GPTQ   URL Share it on

  15   

Llama 2 7B Vietnamese 20K GPTQ is an open-source language model by TheBloke. Features: 7b LLM, VRAM: 3.9GB, Context: 4K, License: llama2, Quantized, LLM Explorer Score: 0.09.

  4-bit Base model:ngoan/llama-2-7b-vi... Base model:quantized:ngoan/lla...   Gptq   Llama   Llama-2-7b   Llama2   Llama2-vietnamese   Quantized   Region:us   Safetensors   Vietnamese
Model Card on HF 🤗: https://huggingface.co/TheBloke/Llama-2-7B-vietnamese-20k-GPTQ 

Llama 2 7B Vietnamese 20K GPTQ Benchmarks

LLME Score: 0.09466
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 2 7B Vietnamese 20K GPTQ (TheBloke/Llama-2-7B-vietnamese-20k-GPTQ)
🌟 Advertise your project 🚀

Llama 2 7B Vietnamese 20K GPTQ Parameters and Internals

Model Type 
text-generation, llama
Use Cases 
Areas:
Research, Development, Language modeling
Applications:
Generating Vietnamese text, Understanding Vietnamese language performance
Primary Use Cases:
Text generation in Vietnamese
Limitations:
Relatively small dataset, Preliminary model
Considerations:
Not for mission-critical applications
Additional Notes 
Preliminary model with plans for refined versions.
Supported Languages 
Vietnamese (Proficient)
Training Details 
Data Sources:
Vietnamese instructions dataset
Data Volume:
20,000 instruction samples
Model Architecture:
Llama 2 7B
LLM NameLlama 2 7B Vietnamese 20K GPTQ
Repository 🤗https://huggingface.co/TheBloke/Llama-2-7B-vietnamese-20k-GPTQ 
Model NameLlama 2 7B Vietnamese 20K
Model CreatorPham Van Ngoan
Base Model(s)  ngoantech/Llama-2-7b-vietnamese-20k   ngoantech/Llama-2-7b-vietnamese-20k
Model Size7b
Required VRAM3.9 GB
Updated2026-04-26
MaintainerTheBloke
Model Typellama
Model Files  3.9 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.34.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Llama 2 7B Vietnamese 20K GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Yarn Llama 2 7B 128K GPTQ128K / 3.9 GB147
Yarn Llama 2 7B 64K GPTQ64K / 3.9 GB261
... 7B 32K Instructions V4 Marlin32K / 4.1 GB80
Aixcoder 7B GPTQ32K / 4.5 GB61
Calm2 7B Chat GPTQ32K / 4.4 GB95
...Calm2 7B Chat GPTQ Calib Ja 1K32K / 4.4 GB35
Llama 2 7B 32K Instruct GPTQ32K / 3.9 GB1927
Codebear 7B 4bit16K / 3.9 GB61
...a 7B Instruct GPTQ Calib Ja 1K16K / 3.9 GB60
Pandalyst 7B V1.2 GPTQ16K / 3.9 GB101
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Llama-2-7B-vietnamese-20k-GPTQ.

Rank the Llama 2 7B Vietnamese 20K GPTQ 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? 53834 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer