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

Upstage Llama 2 70B Instruct V2 GGUF by TheBloke

 »  All LLMs  »  TheBloke  »  Upstage Llama 2 70B Instruct V2 GGUF   URL Share it on

  323   
Base model:quantized:upstage/s... Base model:upstage/solar-0-70b...   En   Gguf   Instruct   Instruction   Llama   Llama2   Quantized   Region:us   Upstage
Model Card on HF 🤗: https://huggingface.co/TheBloke/Upstage-Llama-2-70B-instruct-v2-GGUF 

Upstage Llama 2 70B Instruct V2 GGUF Benchmarks

LLME Score: 0.11143
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Upstage Llama 2 70B Instruct V2 GGUF (TheBloke/Upstage-Llama-2-70B-instruct-v2-GGUF)
🌟 Advertise your project 🚀

Upstage Llama 2 70B Instruct V2 GGUF Parameters and Internals

Model Type 
llama
Use Cases 
Areas:
research, commercial applications
Additional Notes 
The model can handle more than 10k input tokens due to `rope_scaling` feature.
Supported Languages 
English (proficient)
Training Details 
Data Sources:
Orca-style dataset, Alpaca-style dataset
Context Length:
10000
Hardware Used:
A100x8 * 4
Model Architecture:
LLaMA-2
Input Output 
Input Format:
"### User:\n{prompt}\n\n### Assistant:\n"
Accepted Modalities:
text
LLM NameUpstage Llama 2 70B Instruct V2 GGUF
Repository 🤗https://huggingface.co/TheBloke/Upstage-Llama-2-70B-instruct-v2-GGUF 
Model NameLlama 2 70B Instruct v2
Model CreatorUpstage
Base Model(s)  upstage/Llama-2-70b-instruct-v2   upstage/Llama-2-70b-instruct-v2
Model Size70b
Required VRAM29.3 GB
Updated2025-09-23
MaintainerTheBloke
Model Typellama
Instruction-BasedYes
Model Files  29.3 GB   36.1 GB   33.2 GB   29.9 GB   38.9 GB   41.4 GB   39.1 GB   47.5 GB   48.8 GB   47.5 GB
Supported Languagesen
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureAutoModel
Licensellama2

Best Alternatives to Upstage Llama 2 70B Instruct V2 GGUF

Best Alternatives
Context / RAM
Downloads
Likes
CodeLlama 70B Instruct GGUF0K / 25.5 GB215960
Meta Llama 3 70B Instruct GGUF0K / 26.4 GB1334
DAD Model V2 70B Q40K / 42.5 GB100
Swallow 70B Instruct GGUF0K / 29.4 GB5949
...tablelm Instruct Beta 70B GGUF0K / 29.3 GB89912
Leo Hessianai 70B Chat GGUF0K / 29.3 GB2061
Dolphin 2.2 70B GGUF0K / 29.3 GB33117
Llama 2 70B Orca 200K GGUF0K / 29.3 GB65222
Platypus2 70B Instruct GGUF0K / 29.3 GB54510
... 70B Instruct Abliterated LORA0K / 1.7 GB07
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Upstage-Llama-2-70B-instruct-v2-GGUF.

Rank the Upstage Llama 2 70B Instruct V2 GGUF 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? 51544 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