Q2.5 R1 3B by Triangle104

 ยป  All LLMs  ยป  Triangle104  ยป  Q2.5 R1 3B   URL Share it on

  Merged Model   Autotrain compatible Base model:bunnycore/qwen-2.5-... Base model:unsloth/qwen2.5-3b-...   Endpoints compatible   Instruct   Lora   Model-index   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/Triangle104/Q2.5-R1-3B 

Q2.5 R1 3B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Q2.5 R1 3B (Triangle104/Q2.5-R1-3B)
๐ŸŒŸ Advertise your project ๐Ÿš€

Q2.5 R1 3B Parameters and Internals

LLM NameQ2.5 R1 3B
Repository ๐Ÿค—https://huggingface.co/Triangle104/Q2.5-R1-3B 
Base Model(s)  unsloth/Qwen2.5-3B-Instruct   bunnycore/Qwen-2.5-3b-R1-lora_model-v.1   unsloth/Qwen2.5-3B-Instruct   bunnycore/Qwen-2.5-3b-R1-lora_model-v.1
Merged ModelYes
Model Size3b
Required VRAM6.2 GB
Updated2025-07-02
MaintainerTriangle104
Model Typeqwen2
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   1.2 GB: 2-of-2
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.48.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Vocabulary Size151665
LoRA ModelYes
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Q2.5 R1 3B

Best Alternatives
Context / RAM
Downloads
Likes
Saba2 3B128K / 6.2 GB160
Tessa T1 3B117K / 6.2 GB193
UIGEN T1.5 3B117K / 6.2 GB151
Qwen2.5 3B Instruct32K / 6.2 GB2339107268
SmallThinker 3B Preview32K / 6.8 GB45559402
Calme 3.2 Baguette 3B32K / 11 GB41241
Calme 3.1 Baguette 3B32K / 6.2 GB41101
Calme 3.2 Instruct 3B32K / 11 GB41343
Chirp 0132K / 6.2 GB2114
Menda 3B 75032K / 6.2 GB181
Note: green Score (e.g. "73.2") means that the model is better than Triangle104/Q2.5-R1-3B.

Rank the Q2.5 R1 3B 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? 49328 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124