LLM EXPLORER 61,561 MODELS INDEXED

DeepSeek R1 Distill Qwen 7B Abliterated by DuoNeural

By DuoNeural · 78 downloads
HF Repo ↗ Copy URL

DeepSeek R1 Distill Qwen 7B Abliterated is an open-source language model by DuoNeural. Features: 7b LLM, VRAM: 15.2GB, Context: 128K, License: mit, LLM Explorer Score: 0.24.

  Abliteration Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a...   Conversational   Deepseek   Deepseek-r1   Duoneural   En   Qwen2   Reasoning   Refusal-removal   Region:us   Rl-trained   Safetensors   Sharded   Tensorflow   Uncensored
Model Card on HF 🤗: https://huggingface.co/DuoNeural/DeepSeek-R1-Distill-Qwen-7B-Abliterated 

DeepSeek R1 Distill Qwen 7B Abliterated Parameters and Internals

LLM NameDeepSeek R1 Distill Qwen 7B Abliterated
Repository 🤗https://huggingface.co/DuoNeural/DeepSeek-R1-Distill-Qwen-7B-Abliterated 
Base Model(s)  DeepSeek R1 Distill Qwen 7B   deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
Model Size7b
Required VRAM15.2 GB
Updated2026-08-31
MaintainerDuoNeural
Model Typeqwen2
Model Files  5.0 GB: 1-of-4   4.9 GB: 2-of-4   5.0 GB: 3-of-4   0.3 GB: 4-of-4
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version5.10.1
Tokenizer ClassQwen2Tokenizer
Padding Token<｜end▁of▁sentence｜>
Vocabulary Size152064

Best Alternatives to DeepSeek R1 Distill Qwen 7B Abliterated

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 7B Preview986K / 15.2 GB100
Qwen2.5 7B Instruct 1M986K / 15.4 GB52534373
Rewnozom986K / 30.5 GB7421
Hush Qwen2.5 7B V1.2986K / 15.2 GB41
Hush Qwen2.5 7B V1.1986K / 15.2 GB51
Hush Qwen2.5 7B V1.4986K / 15.2 GB81
Hush Qwen2.5 7B Preview986K / 15.2 GB50
Hush Qwen2.5 7B V1.3986K / 15.2 GB102
Hush Qwen2.5 7B RP V1.4 1M986K / 15.2 GB102
Qwen 2.5 7B Exp Sce986K / 15.2 GB102
Note: green Score (e.g. "73.2") means that the model is better than DuoNeural/DeepSeek-R1-Distill-Qwen-7B-Abliterated.