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

Magistrate 3.2 3B Base by macadeliccc

 »  All LLMs  »  macadeliccc  »  Magistrate 3.2 3B Base   URL Share it on

  38   
  Arxiv:2408.10914   Autotrain compatible   Axolotl Base model:finetune:meta-llama... Base model:meta-llama/llama-3.... Dataset:macadeliccc/us-federal... Dataset:macadeliccc/us-supreme...   En   Endpoints compatible   Generated from trainer   Llama   Llama-3   Pytorch   Region:us   Safetensors   Sharded   Spectrum   Tensorflow
Model Card on HF 🤗: https://huggingface.co/macadeliccc/magistrate-3.2-3b-base 

Magistrate 3.2 3B Base Benchmarks

MMLU Pro: 7.65
GPQA: 1.45
MUSR: 7.53
BBH: 6.91
IFEval: 11.59 vs 88 (so35)-86.8%
MATH Lvl 5: 0.68
LLME Score: 0.25055
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Magistrate 3.2 3B Base (macadeliccc/magistrate-3.2-3b-base)

Magistrate 3.2 3B Base Parameters and Internals

Model Type 
text-generation
Training Details 
Data Sources:
US Supreme Court verdicts, federal regulations, laws and treaties, CLL
Data Volume:
~250M tokens
Methodology:
Spectrum top 35% fine tune.
Context Length:
8192
Hardware Used:
multi-GPU, 2 devices
LLM NameMagistrate 3.2 3B Base
Repository 🤗https://huggingface.co/macadeliccc/magistrate-3.2-3b-base 
Base Model(s)  meta-llama/Llama-3.2-3B   meta-llama/Llama-3.2-3B
Model Size3b
Required VRAM6.5 GB
Updated2024-12-21
Maintainermacadeliccc
Model Typellama
Model Files  5.0 GB: 1-of-2   1.5 GB: 2-of-2   0.1 GB   0.0 GB
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensellama3.2
Context Length131072
Model Max Length131072
Transformers Version4.45.0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Magistrate 3.2 3B Base

Best Alternatives
Context / RAM
Downloads
Likes
Llama 3.2 3B Instruct128K / 6.5 GB2165514808
Llama 3.2 3B128K / 6.5 GB1153498412
Hermes 3 Llama 3.2 3B128K / 6.5 GB842797
Llama 3.2 Korean Bllossom 3B128K / 6.5 GB82353130
Calme 3.1 Llamaloi 3B128K / 10.6 GB28911
Llama 3.2 3B Instruct128K / 6.4 GB6393735
Llama Song Stream 3B Instruct128K / 6.5 GB299
Llama Chat Summary 3.2 3B128K / 6.5 GB577
...lama 3.2 Rabbit Ko 3B Instruct128K / 6.5 GB15538
Llama 3.2 3B Instruct128K / 6.5 GB554272
Note: green Score (e.g. "73.2") means that the model is better than macadeliccc/magistrate-3.2-3b-base.

Rank the Magistrate 3.2 3B Base 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