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

Kunoichi Lemon Royale V3 32K 7B by grimjim

 »  All LLMs  »  grimjim  »  Kunoichi Lemon Royale V3 32K 7B   URL Share it on

  28   
  Merged Model   Arxiv:2212.04089   Autotrain compatible Base model:grimjim/kunoichi-le... Base model:grimjim/rogue-encha...   Conversational   Endpoints compatible   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/grimjim/kunoichi-lemon-royale-v3-32K-7B 

Kunoichi Lemon Royale V3 32K 7B Benchmarks

ARC: 66.38 vs 96.7 (so35)-31.4%
HellaSwag: 85.27 vs 95.3 (gpt4)-10.5%
MMLU: 62.88 vs 88.3 (so35)-28.8%
TruthfulQA: 58.35 vs 59 (gpt4)-1.1%
WinoGrande: 78.77 vs 87.5 (gpt4)-10%
GSM8K: 54.21 vs 96.4 (so35)-43.8%
LLME Score: 0.21524
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Kunoichi Lemon Royale V3 32K 7B (grimjim/kunoichi-lemon-royale-v3-32K-7B)

Kunoichi Lemon Royale V3 32K 7B Parameters and Internals

Model Type 
text-generation
Additional Notes 
The merge aimed to enhance variability without affecting coherence. Tested with ChatML instruct templates, temperature 1.0, and minP 0.02. Context length should be at least 16K.
Training Details 
Methodology:
Merge densification using task arithmetic
Context Length:
32000
LLM NameKunoichi Lemon Royale V3 32K 7B
Repository 🤗https://huggingface.co/grimjim/kunoichi-lemon-royale-v3-32K-7B 
Base Model(s)  Rogue Enchantress 32K 7B   ...unoichi Lemon Royale V2 32K 7B   grimjim/rogue-enchantress-32k-7B   grimjim/kunoichi-lemon-royale-v2-32K-7B
Merged ModelYes
Model Size7b
Required VRAM14.5 GB
Updated2024-12-22
Maintainergrimjim
Model Typemistral
Model Files  4.9 GB: 1-of-3   4.9 GB: 2-of-3   4.7 GB: 3-of-3
Model ArchitectureAutoModelForCausalLM
Licensecc-by-nc-4.0
Context Length32768
Model Max Length32768
Transformers Version4.41.1
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Kunoichi Lemon Royale V3 32K 7B

Best Alternatives
Context / RAM
Downloads
Likes
Mistral 7B Instruct V0.332K / 14.5 GB35164741199
Mistral 7B V0.332K / 14.5 GB2833391408
Mistral 7B V0.332K / 14.5 GB77455
Mistral 7B Instruct V0.332K / 14.5 GB73775
Mistral 7B Instruct V0.332K / 14.5 GB32193
Mistralai Mistral 7B V0.332K / 14.5 GB563
...ralai Mistral 7B Instruct V0.332K / 14.5 GB531
Mistral 7B Instruct V0.332K / 14.5 GB90
Mistral 7B V0.232K / 14.5 GB1761
Full V4 Astromistral Final32K / 4.5 GB151
Note: green Score (e.g. "73.2") means that the model is better than grimjim/kunoichi-lemon-royale-v3-32K-7B.

Rank the Kunoichi Lemon Royale V3 32K 7B 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? 40066 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 v20241217
  Support LLM Explorer