LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Saba2 3B by Sakalti

 »  All LLMs  »  Sakalti  »  Saba2 3B   URL Share it on

  330   
  Autotrain compatible Base model:finetune:unsloth/qw... Base model:unsloth/qwen2.5-3b-...   Conversational   En   Endpoints compatible   Instruct   Qwen2   Region:us   Safetensors   Sft   Sharded   Tensorflow   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/Sakalti/Saba2-3B 

Saba2 3B Benchmarks

MMLU Pro: 2.33
GPQA: 1.57
MUSR: 7.25
BBH: 2
IFEval: 28.65 vs 88 (so35)-67.4%
LLME Score: 0.29663
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Saba2 3B (Sakalti/Saba2-3B)

Saba2 3B Parameters and Internals

LLM NameSaba2 3B
Repository 🤗https://huggingface.co/Sakalti/Saba2-3B 
Base Model(s)  unsloth/Qwen2.5-3B-Instruct   unsloth/Qwen2.5-3B-Instruct
Model Size3b
Required VRAM6.2 GB
Updated2025-02-05
MaintainerSakalti
Model Typeqwen2
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   1.2 GB: 2-of-2
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length131072
Model Max Length131072
Transformers Version4.47.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|PAD_TOKEN|>
Vocabulary Size151936
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Saba2 3B

Best Alternatives
Context / RAM
Downloads
Likes
SmallThinker 3B Preview32K / 6.8 GB130211379
Qwen2.5 3B Instruct32K / 6.2 GB326544158
Calme 3.2 Instruct 3B32K / 11 GB30191
Calme 3.1 Baguette 3B32K / 6.2 GB30081
Calme 3.2 Baguette 3B32K / 11 GB29101
Dria Agent A 3B32K / 6.2 GB146548
Calme 3.1 Instruct 3B32K / 11 GB29743
Qwen2.5 Coder 3B Instruct32K / 6.2 GB3525934
...M V1.5 Base QwQ Qwen 2.5 O1 3B32K / 6.2 GB1782
Bio Medical 3B CoT 01202532K / 6.2 GB1539
Note: green Score (e.g. "73.2") means that the model is better than Sakalti/Saba2-3B.

Rank the Saba2 3B Capabilities

🆘 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! 🌟

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? 42565 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227
  Support LLM Explorer