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 70B GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Llama 2 70B GPTQ   URL Share it on

  4597   
  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-2-70B-GPTQ 

Llama 2 70B GPTQ Benchmarks

LLME Score: 0.12701
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 2 70B GPTQ (TheBloke/Llama-2-70B-GPTQ)
🌟 Advertise your project 🚀

Llama 2 70B GPTQ Parameters and Internals

Model Type 
text-generation
Use Cases 
Applications:
Chat assistants, Natural language generation
Primary Use Cases:
Assistant-like chat, GPTQ quantized for GPU inference
Limitations:
Testing conducted in English, outputs in other languages are out-of-scope
Considerations:
Compliance with Meta's Acceptable Use Policy
Additional Notes 
Model architecture uses 4-bit quantized versions for different VRAM requirements and inference quality optimization; supported by AutoGPTQ
Training Details 
Data Sources:
Publicly available online data, Publicly available instruction datasets, Over one million new human-annotated examples
Data Volume:
2 trillion tokens for pretraining
Methodology:
Auto-regressive language modeling with transformer architecture. Fine-tuned with supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF).
Context Length:
4096
Training Time:
Llama 2 70B required 1720320 GPU hours
Hardware Used:
Meta's Research Super Cluster, Production clusters, 3.3M GPU hours on A100-80GB GPUs
Model Architecture:
Auto-regressive transformer
Safety Evaluation 
Methodologies:
Human evaluations, Internal benchmarks
Findings:
Outperformed open-source chat models on benchmarks, On par with closed-source models like ChatGPT for helpfulness and safety
Risk Categories:
Misinformation, Bias
Ethical Considerations:
Testing conducted in English and has not covered all scenarios; may produce inaccurate or biased outputs
Responsible Ai Considerations 
Fairness:
Testing conducted indicates model may produce inaccurate, biased outputs
Transparency:
Safety testing and tuning should be performed for specific applications
Accountability:
Developers need to ensure safety before deploying applications
Mitigation Strategies:
Use safety testing and tuning tailored to specific applications
Input Output 
Input Format:
Text input
Accepted Modalities:
Text
Output Format:
Text output
LLM NameLlama 2 70B GPTQ
Repository 🤗https://huggingface.co/TheBloke/Llama-2-70B-GPTQ 
Model NameLlama 2 70B
Model CreatorMeta Llama 2
Base Model(s)  Llama 2 70B Hf   meta-llama/Llama-2-70b-hf
Model Size70b
Required VRAM35.3 GB
Updated2025-09-23
MaintainerTheBloke
Model Typellama
Model Files  35.3 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 70B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct AutoRound GPTQ 4bit128K / 39.9 GB12716
...B Instruct AutoRound GPTQ 4bit128K / 39.9 GB10590
...ama 3.1 70B Instruct Gptq 4bit128K / 39.9 GB244
Opus V1.2 70B Marlin32K / 36.4 GB50
MoMo 70B Lora 1.8.4 DPO GPTQ32K / 41.3 GB81
MoMo 70B Lora 1.8.6 DPO GPTQ32K / 41.3 GB51
Midnight Miqu 70B V1.5 GPTQ32G31K / 40.7 GB1894
Tess 70B V1.6 Marlin31K / 36.3 GB71
...Midnight Miqu 70B V1.0 GPTQ32G31K / 40.7 GB72
Senku 70B GPTQ 4bit31K / 36.7 GB61
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Llama-2-70B-GPTQ.

Rank the Llama 2 70B 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? 51545 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