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

ORCA LLaMA 70B QLoRA GPTQ by TheBloke

What open-source LLMs or SLMs are you in search of? 18857 in total.

 ยป  All LLMs  ยป  TheBloke  ยป  ORCA LLaMA 70B QLoRA GPTQ   URL Share it on

  Arxiv:2306.02707   4-bit   Autotrain compatible Base model:fangloveskari/orca ...   En   Gptq   Has space   Instruct   License:llama2   Llama   Quantized   Region:us   Safetensors

ORCA LLaMA 70B QLoRA GPTQ Benchmarks

Rank the ORCA LLaMA 70B QLoRA 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  
ORCA LLaMA 70B QLoRA GPTQ (TheBloke/ORCA_LLaMA_70B_QLoRA-GPTQ)

Best Alternatives to ORCA LLaMA 70B QLoRA GPTQ

Best Alternatives
HF Rank
Context/RAM
Downloads
Likes
Dolphin 2.2 70B70.64K / 138 GB167143
SOLAR 0 70B 16bit70.114K / 138 GB2875250
Platypus2 70B Instruct69.34K / 138 GB3323173
MegaDolphin 120B68.914K / 240.7 GB242361
ORCA LLaMA 70B QLoRA67.64K / 138 GB215252
Platypus QLoRA LLaMA 70b67.574K / 138 GB20823
Llama 2 70B Instruct67.382K / 138 GB196662
Instruct Llama70B Dolly15k66.424K / 138 GB34950
Swallow 70B Instruct Hf65.744K / 139.1 GB1326933
Dolphin 2.2 70B GPTQ61.94K / 35.3 GB105
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/ORCA_LLaMA_70B_QLoRA-GPTQ.

ORCA LLaMA 70B QLoRA GPTQ Parameters and Internals

LLM NameORCA LLaMA 70B QLoRA GPTQ
RepositoryOpen on ๐Ÿค— 
Model NameORCA LLaMA 70B QLoRA
Model Creatorfangloveskari
Base Model(s)  ORCA LLaMA 70B QLoRA   fangloveskari/ORCA_LLaMA_70B_QLoRA
Model Size70b
Required VRAM35.3 GB
Updated2024-02-28
MaintainerTheBloke
Model Typellama
Instruction-BasedYes
Model Files  35.3 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.31.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Initializer Range0.02
Torch Data Typefloat16
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024022003