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

NarumashiRTS V2 by Alsebay

 »  All LLMs  »  Alsebay  »  NarumashiRTS V2   URL Share it on

  28   
  Autotrain compatible Base model:finetune:sanjiwatsu... Base model:sanjiwatsuki/kunoic...   En   Endpoints compatible   Mistral   Pytorch   Region:us   Roleplay   Safetensors   Sft   Sharded   Tensorflow   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/Alsebay/NarumashiRTS-V2 

NarumashiRTS V2 Benchmarks

ARC: 68.52 vs 96.7 (so35)-29.1%
HellaSwag: 86.15 vs 95.3 (gpt4)-9.6%
MMLU: 64.19 vs 88.3 (so35)-27.3%
TruthfulQA: 64.54 vs 59 (gpt4)9.4%
WinoGrande: 79.64 vs 87.5 (gpt4)-9%
GSM8K: 67.1 vs 96.4 (so35)-30.4%
LLME Score: 0.18475
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
NarumashiRTS V2 (Alsebay/NarumashiRTS-V2)

NarumashiRTS V2 Parameters and Internals

Model Type 
text-generation-inference, unsloth, mistral, trl, sft, Roleplay, roleplay
Additional Notes 
V2 have more epochs and it is recommended to use V2.1.
Training Details 
Data Sources:
TSF dataset
Methodology:
Finetuned with rough translate dataset, to increase the accuracy in TSF theme, which is not quite popular.
LLM NameNarumashiRTS V2
Repository 🤗https://huggingface.co/Alsebay/NarumashiRTS-V2 
Base Model(s)  Kunoichi DPO V2 7B   SanjiWatsuki/Kunoichi-DPO-v2-7B
Model Size7b
Required VRAM14.4 GB
Updated2024-12-03
MaintainerAlsebay
Model Typemistral
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3   4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licensecc-by-nc-4.0
Context Length8192
Model Max Length8192
Transformers Version4.38.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to NarumashiRTS V2

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB250515
MegaBeam Mistral 7B 512K512K / 14.4 GB396350
SpydazWeb AI HumanAI RP512K / 14.4 GB121
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB365116
Hebrew Mistral 7B 200K256K / 30 GB2257115
Astral 256K 7B V2250K / 14.4 GB120
Astral 256K 7B250K / 14.4 GB60
Test001128K / 14.5 GB90
Note: green Score (e.g. "73.2") means that the model is better than Alsebay/NarumashiRTS-V2.

Rank the NarumashiRTS V2 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? 45019 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