DeepScaleR 1.5B Preview by unsloth

 ยป  All LLMs  ยป  unsloth  ยป  DeepScaleR 1.5B Preview   URL Share it on

  Autotrain compatible Base model:agentica-org/deepsc... Base model:finetune:agentica-o...   Conversational   Deepseek   En   Endpoints compatible   Qwen   Qwen2   Region:us   Safetensors   Unsloth

DeepScaleR 1.5B Preview Benchmarks

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

DeepScaleR 1.5B Preview Parameters and Internals

LLM NameDeepScaleR 1.5B Preview
Repository ๐Ÿค—https://huggingface.co/unsloth/DeepScaleR-1.5B-Preview 
Base Model(s)  agentica-org/DeepScaleR-1.5B-Preview   agentica-org/DeepScaleR-1.5B-Preview
Model Size1.5b
Required VRAM3.5 GB
Updated2025-06-11
Maintainerunsloth
Model Typeqwen2
Model Files  3.5 GB
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licensemit
Context Length24576
Model Max Length24576
Transformers Version4.49.0.dev0
Tokenizer ClassLlamaTokenizerFast
Padding Token<|vision_pad|>
Vocabulary Size151936
Torch Data Typebfloat16
DeepScaleR 1.5B Preview (unsloth/DeepScaleR-1.5B-Preview)

Best Alternatives to DeepScaleR 1.5B Preview

Best Alternatives
Context / RAM
Downloads
Likes
ReaderLM V2500K / 3.1 GB11614647
Reader Lm 1.5B250K / 3.1 GB1499597
DeepSeek R1 Distill Qwen 1.5B128K / 3.5 GB13131361219
...n Research Reasoning Qwen 1.5B128K / 3.5 GB4536143
DeepScaleR 1.5B Preview128K / 7.1 GB108115558
Qwen2.5 1.5B128K / 3.1 GB544103104
OpenMath Nemotron 1.5B128K / 3.1 GB667322
DeepCoder 1.5B Preview128K / 7.1 GB254865
AceInstruct 1.5B128K / 3.5 GB358620
AlphaMaze V0.2 1.5B128K / 3.5 GB880191
Note: green Score (e.g. "73.2") means that the model is better than unsloth/DeepScaleR-1.5B-Preview.

Rank the DeepScaleR 1.5B Preview 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? 48079 in total.

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