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

CalmeRys 78B Orpo V0.1 by dfurman

 »  All LLMs  »  dfurman  »  CalmeRys 78B Orpo V0.1   URL Share it on

  45   

CalmeRys 78B Orpo V0.1 is an open-source language model by dfurman. Features: 78b LLM, VRAM: 156.6GB, Context: 32K, License: mit, LLM Explorer Score: 0.31.

  Autotrain compatible Base model:finetune:maziyarpan... Base model:maziyarpanahi/calme...   Chatml   Conversational Dataset:mlabonne/orpo-dpo-mix-...   En   Model-index   Orpo   Qwen2   Region:us   Safetensors   Sft   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/dfurman/CalmeRys-78B-Orpo-v0.1 

CalmeRys 78B Orpo V0.1 Benchmarks

MMLU Pro: 66.8
GPQA: 20.02
MUSR: 36.37
BBH: 61.92
IFEval: 81.63 vs 88 (so35)-7.2%
MATH Lvl 5: 40.63
LLME Score: 0.31352
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
CalmeRys 78B Orpo V0.1 (dfurman/CalmeRys-78B-Orpo-v0.1)
🌟 Advertise your project 🚀

CalmeRys 78B Orpo V0.1 Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
text generation
Applications:
agentic capabilities, roleplaying, reasoning, multi-turn conversations, long context coherence
Additional Notes 
Model is fine-tuned for generalist language tasks including multiple use cases as stated.
Supported Languages 
en (native)
Training Details 
Data Sources:
mlabonne/orpo-dpo-mix-40k
LLM NameCalmeRys 78B Orpo V0.1
Repository 🤗https://huggingface.co/dfurman/CalmeRys-78B-Orpo-v0.1 
Model Creatordfurman
Base Model(s)  MaziyarPanahi/calme-2.4-rys-78b   MaziyarPanahi/calme-2.4-rys-78b
Model Size78b
Required VRAM156.6 GB
Updated2025-09-23
Maintainerdfurman
Model Typeqwen2
Model Files  4.5 GB: 1-of-33   5.0 GB: 2-of-33   4.8 GB: 3-of-33   4.8 GB: 4-of-33   4.8 GB: 5-of-33   5.0 GB: 6-of-33   4.8 GB: 7-of-33   4.8 GB: 8-of-33   4.8 GB: 9-of-33   5.0 GB: 10-of-33   4.8 GB: 11-of-33   4.8 GB: 12-of-33   4.8 GB: 13-of-33   5.0 GB: 14-of-33   4.8 GB: 15-of-33   4.8 GB: 16-of-33   4.8 GB: 17-of-33   5.0 GB: 18-of-33   4.8 GB: 19-of-33   4.8 GB: 20-of-33   4.8 GB: 21-of-33   5.0 GB: 22-of-33   4.8 GB: 23-of-33   4.8 GB: 24-of-33   4.8 GB: 25-of-33   5.0 GB: 26-of-33   4.8 GB: 27-of-33   4.8 GB: 28-of-33   4.8 GB: 29-of-33   5.0 GB: 30-of-33   4.8 GB: 31-of-33   4.0 GB: 32-of-33   2.5 GB: 33-of-33   0.0 GB
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licensemit
Context Length32768
Model Max Length32768
Transformers Version4.44.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|im_end|>
Vocabulary Size151646
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to CalmeRys 78B Orpo V0.1

Best Alternatives
Context / RAM
Downloads
Likes
Calme 3.2 Instruct 78B32K / 207.1 GB864195
Calme 3.1 Instruct 78B32K / 207.1 GB406
Calme 2.4 Rys 78B32K / 201.4 GB1247
Calme 2.1 Rys 78B32K / 201.4 GB373
Calme 2.3 Rys 78B32K / 201.4 GB124
Calme 2.2 Rys 78B32K / 201.4 GB153
RYS XLarge Base32K / 155.5 GB358
BBAI 78B Calme 3 1 Ties32K / 54.4 GB50
Calme Ties2 78B32K / 156.7 GB51
Calme Ties 78B32K / 156.7 GB41
Note: green Score (e.g. "73.2") means that the model is better than dfurman/CalmeRys-78B-Orpo-v0.1.

Rank the CalmeRys 78B Orpo V0.1 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