LLM Explorer: A Curated Large Language Model Directory and Analytics  // 

Aurelian V0.5 70B Rope8 32K 2.4bpw H6 EXL2 by grimulkan

What open-source LLMs or SLMs are you in search of? 18732 in total.

 ยป  All LLMs  ยป  grimulkan  ยป  Aurelian V0.5 70B Rope8 32K 2.4bpw H6 EXL2   URL Share it on

  Autotrain compatible   Endpoints compatible   Exl2   Fp16   License:unknown   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Rank the Aurelian V0.5 70B Rope8 32K 2.4bpw H6 EXL2 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  
Aurelian V0.5 70B Rope8 32K 2.4bpw H6 EXL2 (grimulkan/aurelian-v0.5-70b-rope8-32K-2.4bpw_h6_exl2)

Best Alternatives to Aurelian V0.5 70B Rope8 32K 2.4bpw H6 EXL2

Best Alternatives
HF Rank
Context/RAM
Downloads
Likes
XuanYuan 70B79.558K / 138.3 GB69042
Tigerbot 70B Chat V277.924K / 139.2 GB2949
QuartetAnemoi 70B T0.000176.8631K / 137.8 GB50912
Miqu 70B Alpaca DPO76.631K / 138.7 GB6453
BoreanGale 70B76.4832K / 137.8 GB9074
Tigerbot 70B Chat V475.954K / 139.2 GB7091
OrcaHermes Mistral 70B Miqu75.5131K / 138 GB671
Senku 70B Full75.3631K / 138.7 GB1677106
Tulu 2 DPO 70B73.778K / 138 GB3347134
Aurora Nights 70B V1.073.774K / 137.8 GB169013
Note: green Score (e.g. "73.2") means that the model is better than grimulkan/aurelian-v0.5-70b-rope8-32K-2.4bpw_h6_exl2.

Aurelian V0.5 70B Rope8 32K 2.4bpw H6 EXL2 Parameters and Internals

LLM NameAurelian V0.5 70B Rope8 32K 2.4bpw H6 EXL2
RepositoryOpen on ๐Ÿค— 
Model Size70b
Required VRAM21.3 GB
Updated2024-02-21
Maintainergrimulkan
Model Typellama
Model Files  4.3 GB: 1-of-5   4.3 GB: 2-of-5   4.3 GB: 3-of-5   4.2 GB: 4-of-5   4.2 GB: 5-of-5
Quantization Typefp16|exl2
Model ArchitectureLlamaForCausalLM
Licenseunknown
Context Length4096
Model Max Length4096
Transformers Version4.34.1
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Initializer Range0.02
Torch Data Typefloat16
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024022003