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

Starcoderplus Guanaco GPT4 15B V1.0 GPTQ by TheBloke

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

 ยป  All LLMs  ยป  TheBloke  ยป  Starcoderplus Guanaco GPT4 15B V1.0 GPTQ   URL Share it on

  4-bit   Autotrain compatible   Codegen   Dataset:guanaco   En   Gpt bigcode   Gptq   License:apache-2.0   Quantized   Region:us   Safetensors

Rank the Starcoderplus Guanaco GPT4 15B 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  
Starcoderplus Guanaco GPT4 15B V1.0 GPTQ (TheBloke/Starcoderplus-Guanaco-GPT4-15B-V1.0-GPTQ)

Best Alternatives to Starcoderplus Guanaco GPT4 15B V1.0 GPTQ

Best Alternatives
HF Rank
WizardCoder 15B 1.0 GPTQ0K / 9.2 GB302175
...ardCoder Guanaco 15B V1.0 GPTQ0K / 9.2 GB216
...ardCoder Guanaco 15B V1.1 GPTQ0K / 9.2 GB1913
Minotaur 15B GPTQ0K / 9.2 GB29
Starcoder 15b 8bit0K /  GB24
Starcoder 15b 4bit0K /  GB52
WizardCoder 15B V1.0 8bit0K / 16.5 GB101
MoTCoder 15B V1.00K / 30.9 GB72
WizardCoder 15B V1.00K / 31 GB5393717
WizardCoder Guanaco 15B V1.10K / 31 GB269911

Starcoderplus Guanaco GPT4 15B V1.0 GPTQ Parameters and Internals

LLM NameStarcoderplus Guanaco GPT4 15B V1.0 GPTQ
RepositoryOpen on ๐Ÿค— 
Model Size15b
Required VRAM9.2 GB
Model Typegpt_bigcode
Model Files  9.2 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Generates CodeYes
Model ArchitectureGPTBigCodeForCausalLM
Transformers Version4.28.1
Tokenizer ClassGPT2Tokenizer
Vocabulary Size49152
Initializer Range0.02
Torch Data Typefloat32
Activation Functiongelu
Attention Dropout0.1
Embedding Dropout0.1
Layer Norm Epsilon1.0E-5
Summary First Dropout0.1
Summary Typecls_index
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024022003