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

Narumashi 11B V0.9 by Alsebay

 »  All LLMs  »  Alsebay  »  Narumashi 11B V0.9   URL Share it on

  54   
  Autotrain compatible Base model:finetune:sao10k/fim... Base model:sao10k/fimbulvetr-1...   En   Endpoints compatible   Llama   Region:us   Roleplay   Safetensors   Sft   Sharded   Tensorflow   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/Alsebay/Narumashi-11B-v0.9 

Narumashi 11B V0.9 Benchmarks

ARC: 68.69 vs 96.7 (so35)-29%
HellaSwag: 86.09 vs 95.3 (gpt4)-9.7%
MMLU: 64.02 vs 88.3 (so35)-27.5%
TruthfulQA: 56.17 vs 59 (gpt4)-4.8%
WinoGrande: 81.85 vs 87.5 (gpt4)-6.5%
LLME Score: 0.21501
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Narumashi 11B V0.9 (Alsebay/Narumashi-11B-v0.9)

Narumashi 11B V0.9 Parameters and Internals

Model Type 
text-generation-inference, transformers, unsloth, llama, trl, sft, Roleplay, roleplay
Additional Notes 
This model focuses on roleplay and TSF content, utilizing a finetuned Chinese Novels dataset for increased accuracy in TSF themes. The model may exhibit less similar GPT-like responses.
Training Details 
Data Sources:
Chinese Novels dataset
Data Volume:
60% skinsuit, 25% possession, 5% transform(shapeshift), 10% other
Methodology:
Traditional methods and [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
Context Length:
8000
Model Architecture:
Finetuned from Sao10K/Fimbulvetr-11B-v2 with a focus on TSF themes.
LLM NameNarumashi 11B V0.9
Repository 🤗https://huggingface.co/Alsebay/Narumashi-11B-v0.9 
Base Model(s)  Fimbulvetr 11B V2   Sao10K/Fimbulvetr-11B-v2
Model Size11b
Required VRAM21.4 GB
Updated2024-12-03
MaintainerAlsebay
Model Typellama
Model Files  4.9 GB: 1-of-5   5.0 GB: 2-of-5   4.9 GB: 3-of-5   4.9 GB: 4-of-5   1.7 GB: 5-of-5
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-4.0
Context Length8192
Model Max Length8192
Transformers Version4.40.0
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Narumashi 11B V0.9

Best Alternatives
Context / RAM
Downloads
Likes
...ral 11B Omni OP 1K 2048 Ver0.132K / 21.4 GB21210
MIstral 11B Omni OP U1k Ver0.132K / 21.4 GB21160
Llama 3 Synatra 11B V1 20K20K / 23 GB299
Fimbulvetr 11B V2.1 16K16K / 21.4 GB4317
Moistral 11B V38K / 21.4 GB60993
Moistral 11B V28K / 21.4 GB5921
Llama 3 16B Instruct V0.18K / 33.5 GB3145
Moistral 11B V5d E48K / 21.4 GB151
Moistral 11B V5a8K / 21.4 GB201
Moistral 11B V5b8K / 21.4 GB121
Note: green Score (e.g. "73.2") means that the model is better than Alsebay/Narumashi-11B-v0.9.

Rank the Narumashi 11B V0.9 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