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

Megrez 3B Instruct Abliterated by Orion-zhen

 »  All LLMs  »  Orion-zhen  »  Megrez 3B Instruct Abliterated   URL Share it on

  12   
Base model:finetune:infinigenc... Base model:infinigence/megrez-...   Conversational   Dataset:augmxnt/deccp   En   Instruct   Llama   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/Orion-zhen/Megrez-3B-Instruct-abliterated 

Megrez 3B Instruct Abliterated Benchmarks

LLME Score: 0.22684
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Megrez 3B Instruct Abliterated (Orion-zhen/Megrez-3B-Instruct-abliterated)

Megrez 3B Instruct Abliterated Parameters and Internals

LLM NameMegrez 3B Instruct Abliterated
Repository 🤗https://huggingface.co/Orion-zhen/Megrez-3B-Instruct-abliterated 
Base Model(s)  Megrez 3B Instruct   Infinigence/Megrez-3B-Instruct
Model Size3b
Required VRAM5.8 GB
Updated2025-04-24
MaintainerOrion-zhen
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   0.8 GB: 2-of-2
Supported Languagesen zh
Model ArchitectureLlamaForCausalLM
Licensegpl-3.0
Context Length32768
Model Max Length32768
Transformers Version4.48.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|pad|>
Vocabulary Size122880
Torch Data Typebfloat16

Best Alternatives to Megrez 3B Instruct Abliterated

Best Alternatives
Context / RAM
Downloads
Likes
Llama 3.2 3B Instruct128K / 6.5 GB14562511374
DeepSeek R1 Distill Llama 3B128K / 6.5 GB71111
Llama 3.2 3B RP Toxic Fuse128K / 6.4 GB152
Zeitgeist 3B V1128K / 6.5 GB1055
...lama 3.2 Rabbit Ko 3B Instruct128K / 6.5 GB26238
Orpheus 3B 0.1 Pretrained128K / 6.6 GB30870
ReasoningCore 3B T1 1128K / 6.5 GB561
Llama 3.2 3B ToxicKod128K / 6.4 GB162
Llama 3.2 3B Instruct128K / 6.5 GB12497558
... 3.2 3B Math Instruct RE1 ORPO128K / 6.5 GB480
Note: green Score (e.g. "73.2") means that the model is better than Orion-zhen/Megrez-3B-Instruct-abliterated.

Rank the Megrez 3B Instruct Abliterated 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