Lia 01 by Creekside

 ยป  All LLMs  ยป  Creekside  ยป  Lia 01   URL Share it on

  Autotrain compatible Base model:creekside/qwen-2.5-... Base model:finetune:creekside/...   Conversational Dataset:creekside/grpo-lambda-...   Dataset:openai/gsm8k   En   Endpoints compatible   Grpo   Pytorch   Qwen2   Region:us   Safetensors   Trl   Unsloth
Model Card on HF ๐Ÿค—: https://huggingface.co/Creekside/Lia-01 

Lia 01 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Lia 01 (Creekside/Lia-01)
๐ŸŒŸ Advertise your project ๐Ÿš€

Lia 01 Parameters and Internals

LLM NameLia 01
Repository ๐Ÿค—https://huggingface.co/Creekside/Lia-01 
Base Model(s)  Creekside/Qwen-2.5-GRPO-1e   Creekside/Qwen-2.5-GRPO-1e
Model Size1.5b
Required VRAM3.1 GB
Updated2025-09-23
MaintainerCreekside
Model Typeqwen2
Model Files  3.1 GB   3.1 GB
Supported Languagesen
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 Lia 01

Best Alternatives
Context / RAM
Downloads
Likes
ReaderLM V2500K / 3.1 GB17305701
Reader Lm 1.5B250K / 3.1 GB1411607
DeepSeek R1 Distill Qwen 1.5B128K / 3.5 GB6028611342
...n Research Reasoning Qwen 1.5B128K / 7.1 GB881295216
DeepScaleR 1.5B Preview128K / 7.1 GB28533573
AceInstruct 1.5B128K / 3.5 GB5202920
Qwen2.5 1.5B128K / 3.1 GB261977127
OpenReasoning Nemotron 1.5B128K / 3.1 GB518847
Palmyra Mini128K / 3.5 GB21230
...1 Distill Qwen 1.5B GSPO Basic128K / 3.5 GB18060
Note: green Score (e.g. "73.2") means that the model is better than Creekside/Lia-01.

Rank the Lia 01 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? 51535 in total.

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