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

Calme 3.1 Instruct 78B by MaziyarPanahi

 »  All LLMs  »  MaziyarPanahi  »  Calme 3.1 Instruct 78B   URL Share it on

  212   
  Autotrain compatible   Chat   Conversational   En   English   Finetuned   Instruct   Model-index   Qwen   Qwen2   Qwen2.5   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/MaziyarPanahi/calme-3.1-instruct-78b 

Calme 3.1 Instruct 78B Benchmarks

MMLU Pro: 68.72
GPQA: 19.46
MUSR: 36.5
BBH: 62.41
IFEval: 81.36 vs 88 (so35)-7.5%
MATH Lvl 5: 38.75
LLME Score: 0.41834
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Calme 3.1 Instruct 78B (MaziyarPanahi/calme-3.1-instruct-78b)

Calme 3.1 Instruct 78B Parameters and Internals

LLM NameCalme 3.1 Instruct 78B
Repository 🤗https://huggingface.co/MaziyarPanahi/calme-3.1-instruct-78b 
Model Namecalme-3.1-instruct-78b
Model CreatorMaziyarPanahi
Base Model(s)  MaziyarPanahi/calme-3-selfmerge-qwen2-78b   MaziyarPanahi/calme-3-selfmerge-qwen2-78b
Model Size78b
Required VRAM207.1 GB
Updated2024-12-30
MaintainerMaziyarPanahi
Model Typeqwen2
Instruction-BasedYes
Model Files  5.0 GB: 1-of-67   5.0 GB: 2-of-67   4.5 GB: 3-of-67   4.5 GB: 4-of-67   4.8 GB: 5-of-67   4.8 GB: 6-of-67   4.5 GB: 7-of-67   4.8 GB: 8-of-67   4.8 GB: 9-of-67   4.5 GB: 10-of-67   4.8 GB: 11-of-67   4.8 GB: 12-of-67   4.5 GB: 13-of-67   4.8 GB: 14-of-67   4.8 GB: 15-of-67   4.5 GB: 16-of-67   4.8 GB: 17-of-67   4.8 GB: 18-of-67   4.5 GB: 19-of-67   4.8 GB: 20-of-67   4.8 GB: 21-of-67   4.5 GB: 22-of-67   4.8 GB: 23-of-67   4.8 GB: 24-of-67   4.5 GB: 25-of-67   4.8 GB: 26-of-67   4.8 GB: 27-of-67   4.5 GB: 28-of-67   4.8 GB: 29-of-67   4.8 GB: 30-of-67   4.5 GB: 31-of-67   4.8 GB: 32-of-67   4.8 GB: 33-of-67   4.5 GB: 34-of-67   4.8 GB: 35-of-67   4.8 GB: 36-of-67   4.5 GB: 37-of-67   4.8 GB: 38-of-67   4.8 GB: 39-of-67   4.5 GB: 40-of-67   4.8 GB: 41-of-67   4.8 GB: 42-of-67   4.5 GB: 43-of-67   4.8 GB: 44-of-67
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.46.1
Vocabulary Size151646
Torch Data Typebfloat16

Best Alternatives to Calme 3.1 Instruct 78B

Best Alternatives
Context / RAM
Downloads
Likes
Calme 3.2 Instruct 78B32K / 207.1 GB127840
Note: green Score (e.g. "73.2") means that the model is better than MaziyarPanahi/calme-3.1-instruct-78b.

Rank the Calme 3.1 Instruct 78B 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? 40476 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