LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Reyna CoT 4B V0.1 by aloobun

 »  All LLMs  »  aloobun  »  Reyna CoT 4B V0.1   URL Share it on

  121   
  Autotrain compatible   Conversational   Cot   Custom code Dataset:kaist-ai/cot-collectio...   Endpoints compatible   Finetuned   Qwen2   Region:us   Safetensors   Sharded   Synthetic data   Tensorflow
Model Card on HF 🤗: https://huggingface.co/aloobun/Reyna-CoT-4B-v0.1 

Reyna CoT 4B V0.1 Benchmarks

ARC: 44.71 vs 96.7 (so35)-53.8%
HellaSwag: 71.12 vs 95.3 (gpt4)-25.4%
MMLU: 55.9 vs 88.3 (so35)-36.7%
TruthfulQA: 43.09 vs 59 (gpt4)-27%
WinoGrande: 67.72 vs 87.5 (gpt4)-22.6%
GSM8K: 16.91 vs 96.4 (so35)-82.5%
LLME Score: 0.20307
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Reyna CoT 4B V0.1 (aloobun/Reyna-CoT-4B-v0.1)

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 🤗https://huggingface.co/aloobun/Reyna-CoT-4B-v0.1 
Model Size4b
Required VRAM7.9 GB
Updated2025-02-05
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
Qwarkstar 4B Instruct Preview32K / 9 GB622
Qwarkstar 4B32K / 9 GB1960
Qwen1.5 4B Chat32K / 7.9 GB561638
Qwen1.5 4B32K / 7.9 GB626734
Qwarkstar 4B Instruct32K / 9 GB301
Sailor 4B32K / 7.9 GB2236
Nusantara 4B Indo Chat32K / 7.9 GB1961
Sailor 4B Chat32K / 7.9 GB1852
Qwen 4B Flock 171956496432K / 7.9 GB770
Qwen 4B Flock 171985500232K / 7.9 GB60
Note: green Score (e.g. "73.2") means that the model is better than aloobun/Reyna-CoT-4B-v0.1.

Rank the Reyna CoT 4B V0.1 Capabilities

🆘 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! 🌟

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? 42577 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227
  Support LLM Explorer