Sakura SOLAR Instruct GPTQ by TheBloke

 ยป  All LLMs  ยป  TheBloke  ยป  Sakura SOLAR Instruct GPTQ   URL Share it on

  4-bit   Autotrain compatible Base model:kyujinpy/sakura-sol... Base model:quantized:kyujinpy/...   Conversational   En   Gptq   Instruct   Llama   Quantized   Region:us   Safetensors

Sakura SOLAR Instruct GPTQ Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Sakura SOLAR Instruct GPTQ (TheBloke/Sakura-SOLAR-Instruct-GPTQ)

Sakura SOLAR Instruct GPTQ Parameters and Internals

Model Type 
text-generation
Supported Languages 
en (full proficiency)
Input Output 
Input Format:
### System: {system_message} ### User: {prompt} ### Assistant:
LLM NameSakura SOLAR Instruct GPTQ
Repository ๐Ÿค—https://huggingface.co/TheBloke/Sakura-SOLAR-Instruct-GPTQ 
Model NameSakura Solar Instruct
Model CreatorKyujinHan
Base Model(s)  Sakura SOLAR Instruct   kyujinpy/Sakura-SOLAR-Instruct
Model Size1.7b
Required VRAM6 GB
Updated2024-12-22
MaintainerTheBloke
Model Typesolar
Instruction-BasedYes
Model Files  6.0 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-sa-4.0
Context Length4096
Model Max Length4096
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Sakura SOLAR Instruct GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...uerkrautLM SOLAR Instruct GPTQ8K / 6 GB232
...rautLM UNA SOLAR Instruct GPTQ4K / 6 GB173
...UNA SOLARkrautLM Instruct GPTQ4K / 6 GB212
SmolLM2 1.7B Instruct Bnb 4bit8K / 1 GB14910
SmolLM 1.7B Instruct 4bit2K / 1 GB222
SmolLM 1.7B Instruct 8bit2K / 1.8 GB211
SmolLM2 1.7B Instruct8K / 3.4 GB92671437
SmolTulu 1.7B Reinforced8K / 3.4 GB355
SmolLM2 Math IIO 1.7B Instruct8K / 3.4 GB1058
SmolLM2 1.7 Persona8K / 3.5 GB180
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Sakura-SOLAR-Instruct-GPTQ.

Rank the Sakura SOLAR Instruct 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? 40066 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217