LLM EXPLORER 59,516 MODELS INDEXED

Reyna CoT 4B V0.1 by aloobun

By aloobun · 103 downloads

Reyna CoT 4B V0.1 is an open-source language model by aloobun. Features: 4b LLM, VRAM: 7.9GB, Context: 32K, License: other, LLM Explorer Score: 0.14, Arc: 44.7, HellaSwag: 71.1, MMLU: 55.9, GSM8K: 16.9.

  Conversational   Cot   Custom code Dataset:kaist-ai/cot-collectio...   Endpoints compatible   Finetuned   Qwen2   Region:us   Safetensors   Sharded   Synthetic data   Tensorflow

Reyna CoT 4B V0.1 Parameters and Internals

Model Type 
text generation, causal language model
Use Cases 
Areas:
Research, Chain of Thought tasks
Applications:
Reasoning, Closed Book Question Answering, Ethics
Considerations:
Improvement on CoT for smaller language models.
Additional Notes 
Experiment aimed to improve CoT capabilities.
Training Details 
Data Sources:
kaist-ai/CoT-Collection, euclaise/TinyCoT, teknium/OpenHermes-2.5
Methodology:
Finetuning on CoT tasks such as Reasoning, Closed Book QA, Ethics.
LLM NameReyna CoT 4B V0.1
Repository πŸ€—https://huggingface.co/aloobun/Reyna-CoT-4B-v0.1 
Model Size4b
Required VRAM7.9 GB
Updated2026-06-29
Maintaineraloobun
Model Typeqwen2
Model Files  3.0 GB: 1-of-3   3.0 GB: 2-of-3   1.9 GB: 3-of-3
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.37.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Reyna CoT 4B V0.1

Best Alternatives
Context / RAM
Downloads
Likes
Qwen1.5 4B Chat32K / 7.9 GB1387746
Qwarkstar 4B Instruct Preview32K / 9 GB22
Qwen1.5 4B32K / 7.9 GB1682036
Qwarkstar 4B32K / 9 GB50
Qwarkstar 4B Instruct32K / 9 GB301
Sailor 4B32K / 7.9 GB1266
Sailor 4B Chat32K / 7.9 GB1552
Nusantara 4B Indo Chat32K / 7.9 GB592
Blossom V5 4B32K / 7.9 GB552
Quyen V0.132K / 7.9 GB22912
Note: green Score (e.g. "73.2") means that the model is better than aloobun/Reyna-CoT-4B-v0.1.