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 Chat GPTQ by TheBloke

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

  2448   
  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-Chat-GPTQ 

Llama 2 70B Chat GPTQ Benchmarks

LLME Score: 0.13089
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 Chat GPTQ (TheBloke/Llama-2-70B-Chat-GPTQ)
🌟 Advertise your project 🚀

Llama 2 70B Chat GPTQ Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
Research, Commercial Applications
Applications:
Assistant-like chat, Natural language generation tasks
Primary Use Cases:
Intended for English dialogue and assistant-like functionalities
Limitations:
Not suitable for legal compliance violations, Testing performed primarily in English
Considerations:
Conduct safety testing tailored to specific applications before deployment.
Additional Notes 
Pretraining data cut off in Sep 2022; latest tuning data from July 2023.
Supported Languages 
English (Native)
Training Details 
Data Sources:
A new mix of publicly available online data
Data Volume:
2.0T tokens
Methodology:
Auto regressive transformer with SFT and RLHF
Context Length:
4096
Training Time:
Between January 2023 and July 2023
Hardware Used:
Meta's Research Super Cluster, production clusters for pretraining
Model Architecture:
Optimized transformer architecture
Safety Evaluation 
Methodologies:
Supervised fine-tuning, Reinforcement learning with human feedback, Automatic safety benchmarks
Findings:
On par with closed-source models like ChatGPT and PaLM
Risk Categories:
Inaccurate or biased outputs, Other objectionable responses
Ethical Considerations:
Refer to Responsible Use Guide for detailed information.
Responsible Ai Considerations 
Fairness:
Testing conducted only in English.
Transparency:
Details provided in accompanying documentation.
Accountability:
Meta oversees the outputs, encourages safety testing before deployment.
Mitigation Strategies:
Future versions will incorporate community feedback for improved safety.
Input Output 
Input Format:
Models input text only.
Accepted Modalities:
text
Output Format:
Models generate text only.
Performance Tips:
Ensure VRAM and software requirements are met for optimal performance.
Release Notes 
Version:
GPTQ
Notes:
Multiple GPTQ quantization options; optimized for hardware and requirements.
LLM NameLlama 2 70B Chat GPTQ
Repository 🤗https://huggingface.co/TheBloke/Llama-2-70B-Chat-GPTQ 
Model NameLlama 2 70B Chat
Model CreatorMeta Llama 2
Base Model(s)  Llama 2 70B Chat Hf   meta-llama/Llama-2-70b-chat-hf
Model Size70b
Required VRAM35.3 GB
Updated2025-11-12
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 Chat 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 GB51
MoMo 70B Lora 1.8.6 DPO GPTQ32K / 41.3 GB51
Tess 70B V1.6 Marlin31K / 36.3 GB71
Miqu 1 70B Sf GPTQ31K / 36.7 GB46510
Midnight Miqu 70B V1.5 GPTQ32G31K / 40.7 GB184
...Midnight Miqu 70B V1.0 GPTQ32G31K / 40.7 GB72
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Llama-2-70B-Chat-GPTQ.

Rank the Llama 2 70B Chat 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? 51567 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