Aurora Nights 70B V1.0 GPTQ by TheBloke

 ยป  All LLMs  ยป  TheBloke  ยป  Aurora Nights 70B V1.0 GPTQ   URL Share it on

  Arxiv:2307.11760   4-bit   Autotrain compatible Base model:quantized:sophosymp... Base model:sophosympatheia/aur...   En   Gptq   Llama   Quantized   Region:us   Safetensors

Aurora Nights 70B V1.0 GPTQ Benchmarks

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 GPTQ Parameters and Internals

LLM NameAurora Nights 70B V1.0 GPTQ
Repository ๐Ÿค—https://huggingface.co/TheBloke/Aurora-Nights-70B-v1.0-GPTQ 
Model NameAurora Nights 70B v1.0
Model CreatorSophosympatheia
Base Model(s)  sophosympatheia/Aurora-Nights-70B-v1.0   sophosympatheia/Aurora-Nights-70B-v1.0
Model Size70b
Required VRAM35.3 GB
Updated2024-09-07
MaintainerTheBloke
Model Typellama
Model Files  35.3 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16
Aurora Nights 70B V1.0 GPTQ (TheBloke/Aurora-Nights-70B-v1.0-GPTQ)

Best Alternatives to Aurora Nights 70B V1.0 GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...ama 3.1 70B Instruct Gptq 4bit128K / 39.9 GB4594
Opus V1.2 70B Marlin32K / 36.4 GB60
MoMo 70B Lora 1.8.4 DPO GPTQ32K / 41.3 GB191
MoMo 70B Lora 1.8.6 DPO GPTQ32K / 41.3 GB161
Midnight Miqu 70B V1.5 GPTQ32G31K / 40.7 GB4802
Tess 70B V1.6 Marlin31K / 36.3 GB41
...Midnight Miqu 70B V1.0 GPTQ32G31K / 40.7 GB82
Senku 70B GPTQ 4bit31K / 36.7 GB21
Miqu 1 70B Sf GPTQ31K / 40.7 GB301
Miqu 1 70B Sf GPTQ31K / 36.7 GB249
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Aurora-Nights-70B-v1.0-GPTQ.

Rank the Aurora Nights 70B V1.0 GPTQ Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 35693 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803