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

Josiefied AbliteratedV4 Qwen2.5 14B Inst BaseMerge TIES by CombinHorizon

 »  All LLMs  »  CombinHorizon  »  Josiefied AbliteratedV4 Qwen2.5 14B Inst BaseMerge TIES   URL Share it on

  6   
  Merged Model   Arxiv:2306.01708   Arxiv:2407.10671   Autotrain compatible Base model:goekdeniz-guelmez/j...   Base model:qwen/qwen2.5-14b   Conversational   En   Endpoints compatible   Instruct   Qwen2   Qwen2.5   Region:us   Safetensors   Sharded   Tensorflow   Ties
Model Card on HF 🤗: https://huggingface.co/CombinHorizon/Josiefied-abliteratedV4-Qwen2.5-14B-Inst-BaseMerge-TIES 

Josiefied AbliteratedV4 Qwen2.5 14B Inst BaseMerge TIES Benchmarks

MMLU Pro: 44.21
GPQA: 9.96
MUSR: 12.65
BBH: 48.2
IFEval: 82.4 vs 88 (so35)-6.4%
MATH Lvl 5: 53.17
LLME Score: 0.34133
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Josiefied AbliteratedV4 Qwen2.5 14B Inst BaseMerge TIES (CombinHorizon/Josiefied-abliteratedV4-Qwen2.5-14B-Inst-BaseMerge-TIES)

Josiefied AbliteratedV4 Qwen2.5 14B Inst BaseMerge TIES Parameters and Internals

LLM NameJosiefied AbliteratedV4 Qwen2.5 14B Inst BaseMerge TIES
Repository 🤗https://huggingface.co/CombinHorizon/Josiefied-abliteratedV4-Qwen2.5-14B-Inst-BaseMerge-TIES 
Base Model(s)  Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4   Qwen/Qwen2.5-14B   Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4   Qwen/Qwen2.5-14B
Merged ModelYes
Model Size14b
Required VRAM29.7 GB
Updated2025-04-24
MaintainerCombinHorizon
Model Typeqwen2
Instruction-BasedYes
Model Files  4.9 GB: 1-of-6   5.0 GB: 2-of-6   5.0 GB: 3-of-6   5.0 GB: 4-of-6   5.0 GB: 5-of-6   4.8 GB: 6-of-6
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 Josiefied AbliteratedV4 Qwen2.5 14B Inst BaseMerge TIES

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 14B Instruct 1M986K / 29.6 GB41091306
T3Q Qwen2.5 14B V1.0 E3986K / 29.7 GB167823
ZYH LLM Qwen2.5 14B V4986K / 29.7 GB1096
Qwen2.5 14B 1M YOYO V3986K / 29.7 GB2544
ZYH LLM Qwen2.5 14B V3986K / 29.7 GB1688
Qwen2.5 14B YOYO Latest V2986K / 29.7 GB1290
Impish QWEN 14B 1M986K / 29.7 GB16716
Qwen2.5 14B YOYO V4986K / 29.7 GB284
...14B Instruct 1M GRPO Reasoning986K / 29.7 GB264
Calcium Opus 14B Elite 1M986K / 29.7 GB194
Note: green Score (e.g. "73.2") means that the model is better than CombinHorizon/Josiefied-abliteratedV4-Qwen2.5-14B-Inst-BaseMerge-TIES.

Rank the Josiefied AbliteratedV4 Qwen2.5 14B 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? 46634 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