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

Qwen2.5 MoE 2X7B DeepSeek Abliterated Censored 19B by DavidAU

 »  All LLMs  »  DavidAU  »  Qwen2.5 MoE 2X7B DeepSeek Abliterated Censored 19B   URL Share it on

  10   
  128k context   Autotrain compatible Base model:deepseek-ai/deepsee... Base model:huihui-ai/deepseek-... Base model:merge:deepseek-ai/d... Base model:merge:huihui-ai/dee...   Cognitivecomputations   Conversational   Cot   Deephermes   Deepseek   Endpoints compatible   Fine tune   Hermes   Merge   Moe   Qwen2.5   Qwen2 moe   R1   Reasoning   Region:us   Safetensors   Sharded   Tensorflow   Thinking
Model Card on HF 🤗: https://huggingface.co/DavidAU/Qwen2.5-MOE-2X7B-DeepSeek-Abliterated-Censored-19B 

Qwen2.5 MoE 2X7B DeepSeek Abliterated Censored 19B Benchmarks

MMLU Pro: 7.07
GPQA: 2.01
MUSR: 5.65
BBH: 10.87
IFEval: 28.35 vs 88 (so35)-67.8%
MATH Lvl 5: 24.17
LLME Score: 0.25957
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen2.5 MoE 2X7B DeepSeek Abliterated Censored 19B (DavidAU/Qwen2.5-MOE-2X7B-DeepSeek-Abliterated-Censored-19B)
🌟 Advertise your project 🚀

Qwen2.5 MoE 2X7B DeepSeek Abliterated Censored 19B Parameters and Internals

LLM NameQwen2.5 MoE 2X7B DeepSeek Abliterated Censored 19B
Repository 🤗https://huggingface.co/DavidAU/Qwen2.5-MOE-2X7B-DeepSeek-Abliterated-Censored-19B 
Base Model(s)  DeepSeek R1 Distill Qwen 7B   ...Distill Qwen 7B Abliterated V2   deepseek-ai/DeepSeek-R1-Distill-Qwen-7B   huihui-ai/DeepSeek-R1-Distill-Qwen-7B-abliterated-v2
Model Size19b
Required VRAM38 GB
Updated2025-07-19
MaintainerDavidAU
Model Typeqwen2_moe
Model Files  4.9 GB: 1-of-8   4.9 GB: 2-of-8   5.0 GB: 3-of-8   5.0 GB: 4-of-8   5.0 GB: 5-of-8   5.0 GB: 6-of-8   5.0 GB: 7-of-8   3.2 GB: 8-of-8
Model ArchitectureQwen2MoeForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.46.2
Tokenizer ClassLlamaTokenizer
Padding Token<｜begin▁of▁sentence｜>
Vocabulary Size152064
Torch Data Typebfloat16

Rank the Qwen2.5 MoE 2X7B DeepSeek Abliterated Censored 19B 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? 49901 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 v20241124
  Support LLM Explorer