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

Bellatrix Tiny 1.5B R1 by prithivMLmods

 »  All LLMs  »  prithivMLmods  »  Bellatrix Tiny 1.5B R1   URL Share it on

  97   
  Autotrain compatible Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-1.5b-i...   Conversational   En   Endpoints compatible   Instruct   Qwen2   Region:us   Reinforcement learning   Safetensors   Trl
Model Card on HF 🤗: https://huggingface.co/prithivMLmods/Bellatrix-Tiny-1.5B-R1 

Bellatrix Tiny 1.5B R1 Benchmarks

MMLU Pro: 19.46
GPQA: 6.49
MUSR: 4.57
BBH: 15.86
IFEval: 33.52 vs 88 (so35)-61.9%
MATH Lvl 5: 6.04
LLME Score: 0.30787
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Bellatrix Tiny 1.5B R1 (prithivMLmods/Bellatrix-Tiny-1.5B-R1)

Bellatrix Tiny 1.5B R1 Parameters and Internals

LLM NameBellatrix Tiny 1.5B R1
Repository 🤗https://huggingface.co/prithivMLmods/Bellatrix-Tiny-1.5B-R1 
Base Model(s)  Qwen/Qwen2.5-1.5B-Instruct   Qwen/Qwen2.5-1.5B-Instruct
Model Size1.5b
Required VRAM3.1 GB
Updated2025-03-13
MaintainerprithivMLmods
Model Typeqwen2
Instruction-BasedYes
Model Files  3.1 GB
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.47.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|PAD_TOKEN|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Bellatrix Tiny 1.5B R1

Best Alternatives
Context / RAM
Downloads
Likes
AceInstruct 1.5B128K / 3.5 GB50519
Gte Qwen2 1.5B Instruct128K / 7.1 GB563320184
Bellatrix 1.5B XElite128K / 3.5 GB10612
WiroAI Finance Qwen 1.5B128K / 3.5 GB13229
... Abliterated TIES Qwen2.5 1.5B128K / 3.5 GB290
Miniclaus Qw1.5B UNAMGS128K / 3.5 GB1918
Saba1 1.8B128K / 3.6 GB291
EVA Qwen2.5 1.5B V0.0128K / 3.1 GB1964
Replete Coder Qwen2 1.5B128K / 3.1 GB23323
Qwen2 1.5B Instruct Refine128K / 3.1 GB1760
Note: green Score (e.g. "73.2") means that the model is better than prithivMLmods/Bellatrix-Tiny-1.5B-R1.

Rank the Bellatrix Tiny 1.5B R1 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? 44950 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