Qwen 2.5 GRPO 1e by Creekside

 ยป  All LLMs  ยป  Creekside  ยป  Qwen 2.5 GRPO 1e   URL Share it on

  4bit   Autotrain compatible   Conversational   En   Endpoints compatible   Grpo   Instruct   Quantized   Qwen2   Region:us   Safetensors   Trl   Unsloth

Qwen 2.5 GRPO 1e Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen 2.5 GRPO 1e (Creekside/Qwen-2.5-GRPO-1e)

Qwen 2.5 GRPO 1e Parameters and Internals

LLM NameQwen 2.5 GRPO 1e
Repository ๐Ÿค—https://huggingface.co/Creekside/Qwen-2.5-GRPO-1e 
Base Model(s)  unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit   unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit
Model Size1.5b
Required VRAM3.1 GB
Updated2025-05-31
MaintainerCreekside
Model Typeqwen2
Instruction-BasedYes
Model Files  3.1 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.48.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen 2.5 GRPO 1e

Best Alternatives
Context / RAM
Downloads
Likes
...1.5B Instruct Unsloth Bnb 4bit32K / 1.5 GB173264
Text2SQL 1.5B32K / 3.1 GB3117
Zirel 1.532K / 3.1 GB70
....5 1.5B Instruct SMPO MLX 8bit32K / 1.6 GB2372
...5 Coder 1.5B Instruct Bnb 4bit32K / 1.1 GB44721
Qwen2.5 1.5B Instruct Bnb 4bit32K / 1.1 GB37583
Qwen2.5 1.5B Instruct 4bit32K / 0.9 GB34521
BAI Qwen 2.5 1.5B Reasoning32K / 3.1 GB70
FastApply 1.5B V1.032K / 3.1 GB92332
....5 1.5B Instruct SMPO MLX 4bit32K / 0.9 GB143
Note: green Score (e.g. "73.2") means that the model is better than Creekside/Qwen-2.5-GRPO-1e.

Rank the Qwen 2.5 GRPO 1e 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? 47753 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227