SKY Ko Qwen2.5 3B Instruct SFT by SkyOrbis

 ยป  All LLMs  ยป  SkyOrbis  ยป  SKY Ko Qwen2.5 3B Instruct SFT   URL Share it on

Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-3b-ins...   Instruct   Ko   Qwen2   Region:us   Safetensors   Sharded   Tensorflow

SKY Ko Qwen2.5 3B Instruct SFT 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 Qwen2.5 3B Instruct SFT (SkyOrbis/SKY-Ko-Qwen2.5-3B-Instruct-SFT)

SKY Ko Qwen2.5 3B Instruct SFT Parameters and Internals

LLM NameSKY Ko Qwen2.5 3B Instruct SFT
Repository ๐Ÿค—https://huggingface.co/SkyOrbis/SKY-Ko-Qwen2.5-3B-Instruct-SFT 
Base Model(s)  Qwen/Qwen2.5-3B-Instruct   Qwen/Qwen2.5-3B-Instruct
Model Size3b
Required VRAM12.3 GB
Updated2025-04-05
MaintainerSkyOrbis
Model Typeqwen2
Instruction-BasedYes
Model Files  5.0 GB: 1-of-3   4.9 GB: 2-of-3   2.4 GB: 3-of-3
Supported Languagesko
Model ArchitectureQwen2ForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.46.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typefloat32
Errorsreplace

Best Alternatives to SKY Ko Qwen2.5 3B Instruct SFT

Best Alternatives
Context / RAM
Downloads
Likes
Saba2 3B128K / 6.2 GB70
Tessa T1 3B117K / 6.2 GB903
UIGEN T1.5 3B117K / 6.2 GB241
Qwen2.5 3B Instruct32K / 6.2 GB1191242242
SmallThinker 3B Preview32K / 6.8 GB43485394
Chirp 0132K / 6.2 GB6314
Calme 3.2 Baguette 3B32K / 11 GB30131
Calme 3.1 Baguette 3B32K / 6.2 GB30251
Calme 3.2 Instruct 3B32K / 11 GB30103
Qwen2.5 3B Model Stock V3.132K / 6.8 GB273
Note: green Score (e.g. "73.2") means that the model is better than SkyOrbis/SKY-Ko-Qwen2.5-3B-Instruct-SFT.

Rank the SKY Ko Qwen2.5 3B Instruct SFT 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? 46599 in total.

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