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

Huihui Ai Abliterated Qwen2.5 32B Inst BaseMerge TIES by CombinHorizon

 »  All LLMs  »  CombinHorizon  »  Huihui Ai Abliterated Qwen2.5 32B Inst BaseMerge TIES   URL Share it on

  18   
  Merged Model   Arxiv:2306.01708   Arxiv:2407.10671   Autotrain compatible Base model:huihui-ai/qwen2.5-3...   Base model:qwen/qwen2.5-32b   Conversational   En   Endpoints compatible   Instruct   Model-index   Qwen2   Qwen2.5   Region:us   Safetensors   Sharded   Tensorflow   Ties
Model Card on HF 🤗: https://huggingface.co/CombinHorizon/huihui-ai-abliterated-Qwen2.5-32B-Inst-BaseMerge-TIES 

Huihui Ai Abliterated Qwen2.5 32B Inst BaseMerge TIES Benchmarks

MMLU Pro: 52.45
GPQA: 11.86
MUSR: 12.09
BBH: 56.04
IFEval: 82.06 vs 88 (so35)-6.8%
LLME Score: 0.34308
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Huihui Ai Abliterated Qwen2.5 32B Inst BaseMerge TIES (CombinHorizon/huihui-ai-abliterated-Qwen2.5-32B-Inst-BaseMerge-TIES)

Huihui Ai Abliterated Qwen2.5 32B Inst BaseMerge TIES Parameters and Internals

LLM NameHuihui Ai Abliterated Qwen2.5 32B Inst BaseMerge TIES
Repository 🤗https://huggingface.co/CombinHorizon/huihui-ai-abliterated-Qwen2.5-32B-Inst-BaseMerge-TIES 
Base Model(s)  Qwen/Qwen2.5-32B   huihui-ai/Qwen2.5-32B-Instruct-abliterated   Qwen/Qwen2.5-32B   huihui-ai/Qwen2.5-32B-Instruct-abliterated
Merged ModelYes
Model Size32b
Required VRAM65.8 GB
Updated2025-02-05
MaintainerCombinHorizon
Model Typeqwen2
Instruction-BasedYes
Model Files  5.0 GB: 1-of-14   5.0 GB: 2-of-14   4.9 GB: 3-of-14   4.9 GB: 4-of-14   4.9 GB: 5-of-14   4.9 GB: 6-of-14   4.9 GB: 7-of-14   4.9 GB: 8-of-14   4.9 GB: 9-of-14   4.9 GB: 10-of-14   4.9 GB: 11-of-14   4.9 GB: 12-of-14   4.9 GB: 13-of-14   1.9 GB: 14-of-14
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.46.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Huihui Ai Abliterated Qwen2.5 32B Inst BaseMerge TIES

Best Alternatives
Context / RAM
Downloads
Likes
...y Qwen2.5coder 32B V24.1q 200K195K / 65.8 GB122
...wen2.5 32B Inst BaseMerge TIES128K / 65.8 GB3619
Franqwenstein 35B128K / 69.8 GB2578
EVA Qwen2.5 32B V0.2128K / 65.8 GB345048
...1 Qwen2.5 Instruct 32B Preview128K / 65.8 GB1747
QwQenSeek Coder128K / 65.7 GB584
EVA Qwen2.5 32B V0.0128K / 65.8 GB104826
Qwenstein2.5 32B Instruct128K / 65.5 GB942
EVA Qwen2.5 32B V0.1128K / 65.8 GB99514
Q2.5 32B Slush128K / 65.7 GB1727
Note: green Score (e.g. "73.2") means that the model is better than CombinHorizon/huihui-ai-abliterated-Qwen2.5-32B-Inst-BaseMerge-TIES.

Rank the Huihui Ai Abliterated Qwen2.5 32B Inst BaseMerge TIES 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? 42565 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