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 7B GPTQ by TheBloke

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

  20631   
  Arxiv:2307.09288   4-bit Base model:meta-llama/llama-2-... Base model:quantized:meta-llam...   Deploy:azure   En   Facebook   Gptq   Llama   Llama2   Meta   Pytorch   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/Llama-2-7B-GPTQ 

Llama 2 7B GPTQ Benchmarks

ARC: 52.05 vs 96.7 (so35)-46.2%
HellaSwag: 77.59 vs 95.3 (gpt4)-18.6%
MMLU: 43.99 vs 88.3 (so35)-50.2%
TruthfulQA: 39.32 vs 59 (gpt4)-33.4%
WinoGrande: 72.93 vs 87.5 (gpt4)-16.7%
GSM8K: 5 vs 96.4 (so35)-94.8%
LLME Score: 0.17817
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 GPTQ (TheBloke/Llama-2-7B-GPTQ)
🌟 Advertise your project 🚀

Llama 2 7B GPTQ Parameters and Internals

Model Type 
llama
Use Cases 
Primary Use Cases:
Natural language generation tasks., Dialogue use cases for fine-tuned variants.
Limitations:
Tested primarily in English; may not work predictably for other languages., Potential for inaccurate or biased outputs.
Considerations:
Follow Meta’s Responsible Use Guide.
Additional Notes 
The model's fine-tuned variants (Llama-2-Chat) are optimized for dialogue applications and exhibit improved safety and helpfulness criteria.
Training Details 
Data Volume:
2.0 trillion tokens
Methodology:
Pretraining on publicly available online data and fine-tuning with supervision and reinforcement learning with human feedback.
Context Length:
4096
Training Time:
January 2023 to July 2023
Hardware Used:
Meta's Research Super Cluster, A100-80GB GPUs
Model Architecture:
Auto-regressive language model using an optimized transformer design.
Responsible Ai Considerations 
Mitigation Strategies:
Perform safety testing and tuning specific to applications.
LLM NameLlama 2 7B GPTQ
Repository 🤗https://huggingface.co/TheBloke/Llama-2-7B-GPTQ 
Model NameLlama 2 7B
Model CreatorMeta
Base Model(s)  Llama 2 7B Hf   meta-llama/Llama-2-7b-hf
Model Size7b
Required VRAM3.9 GB
Updated2026-01-28
MaintainerTheBloke
Model Typellama
Model Files  3.9 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.30.2
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 GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Yarn Llama 2 7B 128K GPTQ128K / 3.9 GB207
Yarn Llama 2 7B 64K GPTQ64K / 3.9 GB111
... 7B 32K Instructions V4 Marlin32K / 4.1 GB80
Aixcoder 7B GPTQ32K / 4.5 GB01
Calm2 7B Chat GPTQ32K / 4.4 GB25
...Calm2 7B Chat GPTQ Calib Ja 1K32K / 4.4 GB85
Llama 2 7B 32K Instruct GPTQ32K / 3.9 GB2127
Codebear 7B 4bit16K / 3.9 GB41
CodeLlama 7B Instruct GPTQ16K / 3.9 GB133346
...a 7B Instruct GPTQ Calib Ja 1K16K / 3.9 GB60

Rank the Llama 2 7B 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? 51602 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