UniReason Qwen3 14B RL by ReasoningTransferability

 ยป  All LLMs  ยป  ReasoningTransferability  ยป  UniReason Qwen3 14B RL   URL Share it on

  Arxiv:2507.00432   Autotrain compatible   Conversational   Dataset:math   Dataset:reasoning   En   Endpoints compatible   Math-reasoning   Qwen   Qwen3   Region:us   Research-paper   Rl-grpo   Safetensors   Sharded   Tensorflow   Transferability

UniReason Qwen3 14B RL Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
UniReason Qwen3 14B RL (ReasoningTransferability/UniReason-Qwen3-14B-RL)
๐ŸŒŸ Advertise your project ๐Ÿš€

UniReason Qwen3 14B RL Parameters and Internals

LLM NameUniReason Qwen3 14B RL
Repository ๐Ÿค—https://huggingface.co/ReasoningTransferability/UniReason-Qwen3-14B-RL 
Base Model(s)  qwen3-14b   /qwen3-14b
Model Size14b
Required VRAM29.5 GB
Updated2025-07-11
MaintainerReasoningTransferability
Model Typeqwen3
Model Files  4.9 GB: 1-of-7   5.0 GB: 2-of-7   4.9 GB: 3-of-7   4.8 GB: 4-of-7   4.9 GB: 5-of-7   4.8 GB: 6-of-7   0.2 GB: 7-of-7
Supported Languagesen
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.52.4
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to UniReason Qwen3 14B RL

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 14B40K / 29.7 GB778184206
Dhanishtha 2.0 Preview40K / 29.5 GB39450
Qwen3 14B FP840K / 16.4 GB1307325
Qwen3 14B40K / 29.5 GB1048810
Qwen3 14B Abliterated40K / 29.5 GB200437
GrayLine Qwen3 14B40K / 29.5 GB135124
UIGEN T3 14B Preview40K / 29.5 GB29419
Smoothie Qwen3 14B40K / 29.5 GB28535
...Omega Directive Qwen3 14B V1.140K / 29.5 GB140219
Qwen3 14B MLX Bf1640K / 29.6 GB1283
Note: green Score (e.g. "73.2") means that the model is better than ReasoningTransferability/UniReason-Qwen3-14B-RL.

Rank the UniReason Qwen3 14B RL 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? 49533 in total.

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