SKY Ko Solar 10.7B Lora by SkyOrbis

 ยป  All LLMs  ยป  SkyOrbis  ยป  SKY Ko Solar 10.7B Lora   URL Share it on

  Autotrain compatible   Endpoints compatible   Ko   Llama   Lora   Region:us   Safetensors   Sharded   Tensorflow

SKY Ko Solar 10.7B Lora Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
SKY Ko Solar 10.7B Lora (SkyOrbis/SKY-Ko-Solar-10.7B-lora)

SKY Ko Solar 10.7B Lora Parameters and Internals

Model Type 
Language Model
Additional Notes 
This model is based on the Solar-10.7B, a state-of-the-art language model, and has been fine-tuned using the LoRA. LoRA allows for efficient fine-tuning with fewer parameters, making the model more adaptable and faster to deploy for specific tasks.
Training Details 
Methodology:
Low-Rank Adaptation (LoRA)
Training Time:
15 hours
Hardware Used:
A100
LLM NameSKY Ko Solar 10.7B Lora
Repository ๐Ÿค—https://huggingface.co/SkyOrbis/SKY-Ko-Solar-10.7B-lora 
Model Size10.7b
Required VRAM21.4 GB
Updated2025-02-22
MaintainerSkyOrbis
Model Typellama
Model Files  4.9 GB: 1-of-5   5.0 GB: 2-of-5   4.9 GB: 3-of-5   4.9 GB: 4-of-5   1.7 GB: 5-of-5
Supported Languagesko
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.41.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
LoRA ModelYes
Torch Data Typebfloat16

Best Alternatives to SKY Ko Solar 10.7B Lora

Best Alternatives
Context / RAM
Downloads
Likes
SOLAR 10.7B Instruct V1.0 128K128K / 21.4 GB3194
SOLAR 10.7B V1.0 Instruct 16K16K / 21.4 GB632
SOLAR 10.7B V1.0 Base 16K16K / 21.4 GB690
SauerkrautLM SOLAR Instruct8K / 21.4 GB200946
PiVoT SOLAR 10.7B RP8K / 21.4 GB18587
MetaModelv28K / 21.4 GB20220
Fimbulvetr V2 Kuro Lotus Bf168K / 21.5 GB113
Kazemi 1.2 Solar8K / 21.4 GB00
Bucharest 0.25K / 21.4 GB681
SOLAR 10.7B Instruct V1.04K / 21.4 GB102273621
Note: green Score (e.g. "73.2") means that the model is better than SkyOrbis/SKY-Ko-Solar-10.7B-lora.

Rank the SKY Ko Solar 10.7B Lora 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? 43470 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227