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

Fireball Mistral Nemo Base 2407 V1 DPO2 by EpistemeAI

 »  All LLMs  »  EpistemeAI  »  Fireball Mistral Nemo Base 2407 V1 DPO2   URL Share it on

  18   
  Autotrain compatible Base model:epistemeai/fireball... Base model:finetune:epistemeai...   En   Endpoints compatible   Mistral   Region:us   Safetensors   Sharded   Tensorflow   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/EpistemeAI/Fireball-Mistral-Nemo-Base-2407-v1-DPO2 

Fireball Mistral Nemo Base 2407 V1 DPO2 Benchmarks

MMLU Pro: 26.14
GPQA: 5.59
MUSR: 9.5
BBH: 28.57
IFEval: 18.61 vs 88 (so35)-78.9%
MATH Lvl 5: 3.63
LLME Score: 0.23218
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
🌟 Advertise your project 🚀

Fireball Mistral Nemo Base 2407 V1 DPO2 Parameters and Internals

Model Type 
text-generation-inference, transformers, mistral, trl
Additional Notes 
This model was fine-tuned from EpistemeAI/Fireball-Nemo-Base-2407-sft-v1.
Supported Languages 
en (proficient)
Training Details 
Methodology:
This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.
LLM NameFireball Mistral Nemo Base 2407 V1 DPO2
Repository 🤗https://huggingface.co/EpistemeAI/Fireball-Mistral-Nemo-Base-2407-v1-DPO2 
Base Model(s)  EpistemeAI/Fireball-Nemo-Base-2407-sft-v1   EpistemeAI/Fireball-Nemo-Base-2407-sft-v1
Model Size12.2b
Required VRAM24.5 GB
Updated2025-06-09
MaintainerEpistemeAI
Model Typemistral
Model Files  4.9 GB: 1-of-5   4.9 GB: 2-of-5   4.9 GB: 3-of-5   4.9 GB: 4-of-5   4.9 GB: 5-of-5
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length1024000
Model Max Length1024000
Transformers Version4.44.0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<pad>
Vocabulary Size131072
Torch Data Typebfloat16
Fireball Mistral Nemo Base 2407 V1 DPO2 (EpistemeAI/Fireball-Mistral-Nemo-Base-2407-v1-DPO2)

Best Alternatives to Fireball Mistral Nemo Base 2407 V1 DPO2

Best Alternatives
Context / RAM
Downloads
Likes
...aptain Eris Violet GRPO V0.4201000K / 24.5 GB12522
...ish Mistral Nemo Instruct 24071000K / 24.5 GB772
Violet Twilight V0.21000K / 24.5 GB15932
Mistral Nemo Kurdish1000K / 24.5 GB293
Mergekit Nuslerp Fybnaus1000K / 24.5 GB370
Goldenworking1000K / 24.5 GB60
MMRExCEV GRPO V0.4201000K / 24.5 GB122
Mergekit Nuslerp Sahgtwn1000K / 24.5 GB90
Mergekit Model Stock Lvezkfe1000K / 24.5 GB90
MMR E11000K / 24.5 GB41
Note: green Score (e.g. "73.2") means that the model is better than EpistemeAI/Fireball-Mistral-Nemo-Base-2407-v1-DPO2.

Rank the Fireball Mistral Nemo Base 2407 V1 DPO2 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? 48023 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 v20241124
  Support LLM Explorer