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 7B Instruct Uncensored by Orion-zhen

 »  All LLMs  »  Orion-zhen  »  Qwen2.5 7B Instruct Uncensored   URL Share it on

  3407   
Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-7b-ins...   Conversational Dataset:anthracite-org/kalo-op... Dataset:crystalcareai/intel-dp... Dataset:nobodyexistsontheinter... Dataset:orion-zhen/dpo-toxic-z... Dataset:unalignment/toxic-dpo-...   En   Instruct   Model-index   Qwen   Qwen2   Region:us   Safetensors   Sharded   Tensorflow   Uncensored   Zh
Model Card on HF 🤗: https://huggingface.co/Orion-zhen/Qwen2.5-7B-Instruct-Uncensored 

Qwen2.5 7B Instruct Uncensored Benchmarks

MMLU Pro: 38.07
GPQA: 7.05
MUSR: 13.58
BBH: 35.83
IFEval: 72.04 vs 88 (so35)-18.1%
MATH Lvl 5: 1.36
LLME Score: 0.37329
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen2.5 7B Instruct Uncensored (Orion-zhen/Qwen2.5-7B-Instruct-Uncensored)

Qwen2.5 7B Instruct Uncensored Parameters and Internals

Model Type 
text-generation
Additional Notes 
The model, despite being uncensored, may fail to generate detailed descriptions in certain extreme scenarios possibly due to deletions in the pretraining datasets.
Supported Languages 
zh (native), en (native)
Training Details 
Data Sources:
NobodyExistsOnTheInternet/ToxicQAFinal, anthracite-org/kalo-opus-instruct-22k-no-refusal, Orion-zhen/dpo-toxic-zh, unalignment/toxic-dpo-v0.2, Crystalcareai/Intel-DPO-Pairs-Norefusals
Methodology:
SFT + DPO
LLM NameQwen2.5 7B Instruct Uncensored
Repository 🤗https://huggingface.co/Orion-zhen/Qwen2.5-7B-Instruct-Uncensored 
Base Model(s)  Qwen/Qwen2.5-7B-Instruct   Qwen/Qwen2.5-7B-Instruct
Model Size7b
Required VRAM15.2 GB
Updated2024-12-21
MaintainerOrion-zhen
Model Typeqwen2
Instruction-BasedYes
Model Files  4.9 GB: 1-of-4   4.9 GB: 2-of-4   4.3 GB: 3-of-4   1.1 GB: 4-of-4
Supported Languageszh en
Model ArchitectureQwen2ForCausalLM
Licensegpl-3.0
Context Length32768
Model Max Length32768
Transformers Version4.44.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Quantized Models of the Qwen2.5 7B Instruct Uncensored

Model
Likes
Downloads
VRAM
....5 7B Instruct Uncensored 4bit22544 GB

Best Alternatives to Qwen2.5 7B Instruct Uncensored

Best Alternatives
Context / RAM
Downloads
Likes
...2.5 7B Instruct Abliterated V232K / 15.2 GB322424
...wen2.5 7B Instruct Abliterated32K / 15.2 GB29502
...wen2.5 7B Nerd Uncensored V0.932K / 15.2 GB680
Qwen2 7B Instruct Abliterated32K / 15.2 GB27286
...2.5 7B Instruct Abliterated V332K / 15.2 GB3723
... Coder 7B Instruct Abliterated32K / 15.2 GB2236
Meissa Qwen2.5 7B Instruct32K / 15.2 GB21812
Qwen2.5 7B Gutenberg KTO32K / 14.9 GB354
Qwen 2.5 7B TitanFusion V232K / 15.2 GB171
Qwen2.5 7B HyperMix32K / 15.2 GB191

Rank the Qwen2.5 7B Instruct Uncensored 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? 40013 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 v20241217
  Support LLM Explorer