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

Bepis 9B by ChaoticNeutrals

 »  All LLMs  »  ChaoticNeutrals  »  Bepis 9B   URL Share it on

  5   
  Merged Model   Autotrain compatible   En   Endpoints compatible   Mistral   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/ChaoticNeutrals/Bepis_9B 

Bepis 9B Benchmarks

ARC: 62.54 vs 96.7 (so35)-35.3%
HellaSwag: 80.12 vs 95.3 (gpt4)-15.9%
MMLU: 62.84 vs 88.3 (so35)-28.8%
TruthfulQA: 53.3 vs 59 (gpt4)-9.7%
WinoGrande: 76.48 vs 87.5 (gpt4)-12.6%
GSM8K: 39.12 vs 96.4 (so35)-59.4%
LLME Score: 0.17503
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Bepis 9B (ChaoticNeutrals/Bepis_9B)

Bepis 9B Parameters and Internals

Model Type 
text-generation
Additional Notes 
Bepis_9B is a new 9B model from jeiku, proficient in markdown, with a soulful touch. Its unique merge consists of a balance between three base models: Prodigy_7B, Prima-LelantaclesV6-7b, and Thespis-CurtainCall-7b-v0.2.1.
Training Details 
Data Sources:
AI2 Reasoning Challenge, HellaSwag, MMLU, TruthfulQA, Winogrande, GSM8k
Methodology:
Slices method with sources and layer ranges for merging models.
Model Architecture:
Merge of three models using slices and passthrough methodology.
LLM NameBepis 9B
Repository 🤗https://huggingface.co/ChaoticNeutrals/Bepis_9B 
Merged ModelYes
Model Size9b
Required VRAM18 GB
Updated2025-05-16
MaintainerChaoticNeutrals
Model Typemistral
Model Files  10.0 GB: 1-of-2   8.0 GB: 2-of-2
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.38.1
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Bepis 9B

Best Alternatives
Context / RAM
Downloads
Likes
Peagle 9B32K / 18 GB80030
Alphacode MALI 9B32K / 17.9 GB10960
MetaMath Mistral Pro32K / 17.9 GB85
Mistral 9B Instruct32K / 35.9 GB330
...onarch Neurotic 9B Passthrough32K / 17.9 GB100
Garbage 9B32K / 17.9 GB83
Notus TheTop 7B Passthrough32K / 18 GB80
Mistral 9B Instruct V0.232K / 17.9 GB53
...raAI Foredoomed 9B EXL 2.8 Bpw32K / 3.7 GB150
...alderaAI Foredoomed 9B EXL 7.032K / 8.8 GB71
Note: green Score (e.g. "73.2") means that the model is better than ChaoticNeutrals/Bepis_9B.

Rank the Bepis 9B 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? 47377 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