LLM EXPLORER 60,277 MODELS INDEXED

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

By DavidAU · 12 downloads
HF Repo ↗ Copy URL

Qwen2.5 MoE 2X7B DeepSeek Abliterated Censored 19B is an open-source language model by DavidAU. Features: 19b LLM, VRAM: 38GB, Context: 128K, MoE, LLM Explorer Score: 0.2.

  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 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
Updated2025-08-25
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

Best Alternatives to Qwen2.5 MoE 2X7B DeepSeek Abliterated Censored 19B

Best Alternatives
Context / RAM
Downloads
Likes
...oder Instruct OlympicCoder 19B32K / 38 GB72
...oder Instruct OlympicCoder 19B32K / 38 GB81
...oder Instruct OlympicCoder 19B32K / 38 GB71
...eek Abliterated UNCensored 19B128K / 38 GB160