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

Athena V1 GPTQ by TheBloke

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

 ยป  All LLMs  ยป  TheBloke  ยป  Athena V1 GPTQ   URL Share it on

  4-bit   Autotrain compatible   Base model:ikaridev/athena-v1   Gptq   License:llama2   Llama   Quantized   Region:us   Safetensors

Athena V1 GPTQ Benchmarks

Rank the Athena V1 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  
Athena V1 GPTQ (TheBloke/Athena-v1-GPTQ)

Best Alternatives to Athena V1 GPTQ

Best Alternatives
HF Rank
Context/RAM
Downloads
Likes
Deita 2B52.352K / 6 GB4880
Orca 2 13B GPTQ51.44K / 7.3 GB184926
Stheno V2 Delta GPTQ50.74K / 7.3 GB273
Athena V4 GPTQ50.24K / 7.3 GB146
Athena V4 AWQ50.24K / 7.2 GB92
Athena V3 GPTQ50.14K / 7.3 GB279
Athena V3 AWQ50.14K / 7.2 GB31
QCammel 13 GPTQ49.24K / 7.3 GB10273
MythoMax Kimiko Mix GPTQ4K / 7.3 GB26
Athena V2 GPTQ4K / 7.3 GB93
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Athena-v1-GPTQ.

Athena V1 GPTQ Parameters and Internals

LLM NameAthena V1 GPTQ
RepositoryOpen on ๐Ÿค— 
Model NameAthena v1
Model CreatorIkariDev
Base Model(s)  Athena V1   IkariDev/Athena-v1
Model Size2b
Required VRAM7.3 GB
Updated2024-02-21
MaintainerTheBloke
Model Typellama
Model Files  7.3 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.32.1
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