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

Llama 2 13B GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Llama 2 13B GPTQ   URL Share it on

  3537   
  Arxiv:2307.09288   4-bit   Autotrain compatible Base model:meta-llama/llama-2-... Base model:quantized:meta-llam...   En   Facebook   Gptq   Llama   Llama2   Meta   Pytorch   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/Llama-2-13B-GPTQ 

Llama 2 13B GPTQ Benchmarks

ARC: 59.13 vs 96.7 (so35)-38.9%
HellaSwag: 81.48 vs 95.3 (gpt4)-14.5%
MMLU: 54.45 vs 88.3 (so35)-38.3%
TruthfulQA: 37.07 vs 59 (gpt4)-37.2%
WinoGrande: 76.16 vs 87.5 (gpt4)-13%
GSM8K: 11.3 vs 96.4 (so35)-88.3%
LLME Score: 0.1526
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 2 13B GPTQ (TheBloke/Llama-2-13B-GPTQ)
🌟 Advertise your project 🚀

Llama 2 13B GPTQ Parameters and Internals

Model Type 
llama
Use Cases 
Areas:
commercial, research
Applications:
assistant-like chat, natural language generation
Primary Use Cases:
Chat models for dialogue
Limitations:
English-focused, not tested in all languages., Potentially unpredictable outputs.
Considerations:
Follow specific input formatting to align with intended use cases.
Additional Notes 
Compatible with AutoGPTQ and major GPTQ clients. Choose quantization parameters based on hardware needs.
Supported Languages 
en (fluent)
Training Details 
Data Sources:
Publicly available online data
Data Volume:
2 trillion tokens
Methodology:
Pretrained and fine-tuned using supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF)
Context Length:
4096
Training Time:
January 2023 to July 2023
Hardware Used:
A100-80GB GPUs
Model Architecture:
Optimized transformer architecture.
Safety Evaluation 
Methodologies:
Internal evaluations library
Findings:
May produce inaccurate, biased or objectionable responses; testing primarily in English.
Risk Categories:
TruthfulQA, Toxigen
Ethical Considerations:
Before deploying applications, perform safety testing tailored to your use case.
Responsible Ai Considerations 
Fairness:
Testing primarily in English, does not guarantee unbiased outputs in all languages.
Transparency:
Evaluation data and results are disclosed.
Accountability:
Developers responsible for application-specific safety testing.
Mitigation Strategies:
Community feedback and iterative improvements.
Input Output 
Input Format:
Text prompt
Accepted Modalities:
text
Output Format:
Generated text
Performance Tips:
Select appropriate quantization parameters for VRAM efficiency and accuracy.
Release Notes 
Version:
Llama 2 13B
Date:
July 2023
Notes:
Pretrained on 2 trillion tokens with fine-tuning using RLHF for dialog applications.
LLM NameLlama 2 13B GPTQ
Repository 🤗https://huggingface.co/TheBloke/Llama-2-13B-GPTQ 
Model NameLlama 2 13B
Model CreatorMeta
Base Model(s)  Llama 2 13B Hf   meta-llama/Llama-2-13b-hf
Model Size13b
Required VRAM7.3 GB
Updated2025-09-23
MaintainerTheBloke
Model Typellama
Model Files  7.3 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.32.0.dev0
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 13B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Yarn Llama 2 13B 128K GPTQ128K / 7.3 GB1716
LongAlign 13B 64K GPTQ64K / 7.3 GB61
...boros L2 13B 2 1 YaRN 64K GPTQ64K / 7.3 GB193
Yarn Llama 2 13B 64K GPTQ64K / 7.3 GB131
OrcaMaid V3 13B 32K GPTQ32K / 7.3 GB63
OrcaMaid V2 FIX 13B 32K GPTQ32K / 7.3 GB64
EverythingLM 13B 16K GPTQ16K / 7.3 GB1414
LlongOrca 13B 16K GPT16K / 7.3 GB70
Tinybra 13B GPTQ 32g 4BIT16K / 8 GB61
Tinybra 13B GPTQ 4BIT16K / 7 GB60

Rank the Llama 2 13B 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? 51558 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 v20241124
  Support LLM Explorer