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

Instruct 12B by hakurei

 »  All LLMs  »  hakurei  »  Instruct 12B   URL Share it on

  2569   

Instruct 12B is an open-source language model by hakurei. Features: 12b LLM, VRAM: 47.6GB, Context: 2K, License: apache-2.0, Instruction-Based, HF Score: 38.6, LLM Explorer Score: 0.13, Arc: 42.6, HellaSwag: 66.8, MMLU: 26.8, TruthfulQA: 32, WinoGrande: 63.5, GSM8K: 0.2.

  Code Dataset:hakurei/open-instruct-...   En   Gpt neox   Instruct   Pythia   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/hakurei/instruct-12b 

Instruct 12B Benchmarks

ARC: 42.58 vs 96.7 (so35)-56%
HellaSwag: 66.76 vs 95.3 (gpt4)-29.9%
MMLU: 26.79 vs 88.3 (so35)-69.7%
TruthfulQA: 31.96 vs 59 (gpt4)-45.8%
WinoGrande: 63.46 vs 87.5 (gpt4)-27.5%
GSM8K: 0.23 vs 96.4 (so35)-99.8%
LLME Score: 0.12582
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Instruct 12B (hakurei/instruct-12b)
🌟 Advertise your project 🚀

Instruct 12B Parameters and Internals

Model Type 
text-generation, instruct
Additional Notes 
The model is intended as an open-source alternative to OpenAI's InstructGPT series of models.
Supported Languages 
English (High)
Training Details 
Data Sources:
Open-Instruct v1 dataset
Methodology:
fine-tuning
Input Output 
Input Format:
Two newlines delimiting user input and generated output
Accepted Modalities:
text
Output Format:
text
LLM NameInstruct 12B
Repository 🤗https://huggingface.co/hakurei/instruct-12b 
Model Size12b
Required VRAM47.6 GB
Updated2026-04-11
Maintainerhakurei
Model Typegpt_neox
Instruction-BasedYes
Model Files  9.9 GB: 1-of-5   9.7 GB: 2-of-5   9.7 GB: 3-of-5   10.0 GB: 4-of-5   8.3 GB: 5-of-5
Supported Languagesen
Model ArchitectureGPTNeoXForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.28.0.dev0
Tokenizer ClassGPTNeoXTokenizer
Vocabulary Size50277
Torch Data Typefloat32

Best Alternatives to Instruct 12B

Best Alternatives
Context / RAM
Downloads
Likes
...12B Deduped Synthetic Instruct2K / 47.6 GB23
Chip 12B Instruct Alpha2K / 23.8 GB71

Rank the Instruct 12B 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? 52721 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer