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

Saba1 1.8B by Sakalti

 »  All LLMs  »  Sakalti  »  Saba1 1.8B   URL Share it on

  315   
  Merged Model   Arxiv:2306.01708   Autotrain compatible Base model:micaebe/qwen2.5-1.5...   Base model:sakalti/model-4   Conversational   Endpoints compatible   Instruct   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Sakalti/Saba1-1.8B 

Saba1 1.8B Benchmarks

MMLU Pro: 21.39
GPQA: 4.36
MUSR: 11.02
BBH: 17.53
IFEval: 33.33 vs 88 (so35)-62.1%
MATH Lvl 5: 10.35
LLME Score: 0.33966
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Saba1 1.8B (Sakalti/Saba1-1.8B)

Saba1 1.8B Parameters and Internals

LLM NameSaba1 1.8B
Repository 🤗https://huggingface.co/Sakalti/Saba1-1.8B 
Base Model(s)  micaebe/Qwen2.5-1.5B-Instruct-QwQ   Model 4   micaebe/Qwen2.5-1.5B-Instruct-QwQ   Sakalti/model-4
Merged ModelYes
Model Size1.5b
Required VRAM3.6 GB
Updated2024-12-21
MaintainerSakalti
Model Typeqwen2
Instruction-BasedYes
Model Files  1.0 GB: 1-of-4   1.0 GB: 2-of-4   1.0 GB: 3-of-4   0.6 GB: 4-of-4
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.45.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Saba1 1.8B

Best Alternatives
Context / RAM
Downloads
Likes
Gte Qwen2 1.5B Instruct128K / 7.1 GB54016144
Miniclaus Qw1.5B UNAMGS128K / 3.5 GB1858
Replete Coder Qwen2 1.5B128K / 3.1 GB23323
Qwen2 1.5B Instruct Refine128K / 3.1 GB210
Samantha Qwen2 1.5B128K / 3.1 GB340
Qwen2.5 1.5B Instruct32K / 3.1 GB586994252
Qwen2 1.5B Instruct32K / 3.1 GB190011133
Qwen2.5 Coder 1.5B Instruct32K / 3.1 GB2127251
...struct W8a8 Int Dynamic Weight32K / 3.1 GB20050
...5 1.5B Instruct Abliterated V132K / 3.5 GB4044
Note: green Score (e.g. "73.2") means that the model is better than Sakalti/Saba1-1.8B.

Rank the Saba1 1.8B 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? 40013 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 v20241217
  Support LLM Explorer