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

ReWiz Qwen 2.5 14B by theprint

 »  All LLMs  »  theprint  »  ReWiz Qwen 2.5 14B   URL Share it on

  283   
  4-bit   4bit   Autotrain compatible   Bitsandbytes   Dataset:theprint/rewiz   En   Endpoints compatible   Gguf   Lora   Model-index   Quantized   Qwen2   Region:us   Rewiz   Safetensors   Sft   Sharded   Tensorflow   Theprint   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/theprint/ReWiz-Qwen-2.5-14B 

ReWiz Qwen 2.5 14B Benchmarks

MMLU Pro: 45.47
GPQA: 17.34
MUSR: 15.44
BBH: 44.86
IFEval: 27.85 vs 88 (so35)-68.4%
MATH Lvl 5: 29.23
LLME Score: 0.30533
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
ReWiz Qwen 2.5 14B (theprint/ReWiz-Qwen-2.5-14B)

ReWiz Qwen 2.5 14B Parameters and Internals

LLM NameReWiz Qwen 2.5 14B
Repository 🤗https://huggingface.co/theprint/ReWiz-Qwen-2.5-14B 
Base Model(s)  unsloth/qwen2.5-14b-bnb-4bit   unsloth/qwen2.5-14b-bnb-4bit
Model Size14b
Required VRAM29.7 GB
Updated2025-06-01
Maintainertheprint
Model Files  29.5 GB   7.3 GB   6.7 GB   9.0 GB   8.6 GB   10.5 GB   12.1 GB   15.7 GB   0.1 GB   5.0 GB: 1-of-6   5.0 GB: 2-of-6   5.0 GB: 3-of-6   5.0 GB: 4-of-6   5.0 GB: 5-of-6   4.7 GB: 6-of-6
Supported Languagesen
GGUF QuantizationYes
Quantization Type4bit|gguf
Model ArchitectureAutoModelForCausalLM
Licenseapache-2.0
Model Max Length131072
Is Biasednone
Tokenizer ClassQwen2Tokenizer
Padding Token<|PAD_TOKEN|>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesv_proj|gate_proj|up_proj|q_proj|k_proj|down_proj|o_proj
LoRA Alpha16
LoRA Dropout0
R Param8
Errorsreplace

Best Alternatives to ReWiz Qwen 2.5 14B

Best Alternatives
Context / RAM
Downloads
Likes
Phi3 14B Unsloth Sft Quip 2bit0K / 0.1 GB150
Phi3 14B Unsloth Sft Quip 3bit0K / 0.1 GB140
DeepSeek R1 14B Finetuned0K / 29.7 GB110
MING MoE 14B0K / 0.1 GB240

Rank the ReWiz Qwen 2.5 14B 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? 47770 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