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

Aurora Nights 70B V1.0 by sophosympatheia

 »  All LLMs  »  sophosympatheia  »  Aurora Nights 70B V1.0   URL Share it on

  1045   
  Arxiv:2307.11760   Autotrain compatible   En   Endpoints compatible   Llama   Model-index   Region:us   Safetensors   Sharded   Tensorflow

Aurora Nights 70B V1.0 Benchmarks

ARC: 71.33 vs 96.7 (so35)-26.2%
HellaSwag: 88.33 vs 95.3 (gpt4)-7.3%
MMLU: 70.47 vs 88.3 (so35)-20.2%
TruthfulQA: 62.81 vs 59 (gpt4)6.5%
WinoGrande: 83.35 vs 87.5 (gpt4)-4.7%
GSM8K: 66.34 vs 96.4 (so35)-31.2%
LLME Score: 0.19978
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Aurora Nights 70B V1.0 Parameters and Internals

LLM NameAurora Nights 70B V1.0
Repository 🤗https://huggingface.co/sophosympatheia/Aurora-Nights-70B-v1.0 
Model Size70b
Required VRAM137.8 GB
Updated2024-10-18
Maintainersophosympatheia
Model Typellama
Model Files  8.1 GB: 1-of-17   8.1 GB: 2-of-17   8.2 GB: 3-of-17   8.1 GB: 4-of-17   8.1 GB: 5-of-17   8.1 GB: 6-of-17   8.2 GB: 7-of-17   8.1 GB: 8-of-17   8.1 GB: 9-of-17   8.1 GB: 10-of-17   8.2 GB: 11-of-17   8.1 GB: 12-of-17   8.1 GB: 13-of-17   8.1 GB: 14-of-17   8.2 GB: 15-of-17   8.1 GB: 16-of-17   7.8 GB: 17-of-17
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.36.1
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16
Aurora Nights 70B V1.0 (sophosympatheia/Aurora-Nights-70B-v1.0)

Quantized Models of the Aurora Nights 70B V1.0

Model
Likes
Downloads
VRAM
Aurora Nights 70B V1.0 GGUF820629 GB
Aurora Nights 70B V1.0 AWQ4936 GB
Aurora Nights 70B V1.0 GPTQ1835 GB

Best Alternatives to Aurora Nights 70B V1.0

Best Alternatives
Context / RAM
Downloads
Likes
... 3 70B Instruct Gradient 1048K1024K / 141.9 GB384119
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB28595
Llama3 Function Calling 1048K1024K / 141.9 GB51
...a 3 70B Instruct Gradient 524K512K / 141.9 GB23923
...a 3 70B Instruct Gradient 262K256K / 141.9 GB34455
...ama 3 70B Arimas Story RP V2.0256K / 141.1 GB2313
...ama 3 70B Arimas Story RP V1.5256K / 141.2 GB2762
...ama 3 70B Arimas Story RP V1.6256K / 141.2 GB100
Yi 70B 200K RPMerge Franken195K / 142.4 GB91
...a 3.1 Nemotron 70B Instruct HF128K / 141.9 GB19164471
Note: green Score (e.g. "73.2") means that the model is better than sophosympatheia/Aurora-Nights-70B-v1.0.

Rank the Aurora Nights 70B V1.0 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? 36966 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 v2024072803
  Support LLM Explorer