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

WoonaV1.2 9B by AlexBefest

 »  All LLMs  »  AlexBefest  »  WoonaV1.2 9B   URL Share it on

  62   
  Autotrain compatible Base model:finetune:google/gem... Base model:google/gemma-2-9b-i...   Conversational   Endpoints compatible   Gemma2   Lora   Mylittlepony   Pony   Region:us   Ru   Russian   Safetensors   Sft   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/AlexBefest/WoonaV1.2-9b 

WoonaV1.2 9B Benchmarks

LLME Score: 0.21831
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
WoonaV1.2 9B (AlexBefest/WoonaV1.2-9b)

WoonaV1.2 9B Parameters and Internals

Model Type 
Single language model
Use Cases 
Areas:
artificial intelligence, fan fiction, role-playing games
Applications:
story writing, translating MLP fanfiction, role-playing
Primary Use Cases:
My Little Pony: FIM related tasks, Fanfiction advice, Canonical information retrieval
Additional Notes 
The model focuses on canonical My Little Pony: FIM series knowledge and is not ideal yet, as hallucinations may still occur.
Supported Languages 
ru (Russian)
Training Details 
Data Sources:
My Little Pony: FIM fandom wiki
Methodology:
Trained on augmented synthetic Russian-language data using My Little Pony: FIM wiki as foundation.
Model Architecture:
Based on gemma 9b it
Input Output 
Performance Tips:
Recommend set temperature to 0.3 - 0.5
LLM NameWoonaV1.2 9B
Repository 🤗https://huggingface.co/AlexBefest/WoonaV1.2-9b 
Base Model(s)  Gemma 2 9B It   google/gemma-2-9b-it
Model Size9b
Required VRAM18.6 GB
Updated2025-02-22
MaintainerAlexBefest
Model Typegemma2
Model Files  4.9 GB: 1-of-4   5.0 GB: 2-of-4   5.0 GB: 3-of-4   3.7 GB: 4-of-4
Supported Languagesru
Model ArchitectureGemma2ForCausalLM
Licensegemma
Context Length8192
Model Max Length8192
Transformers Version4.44.2
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
LoRA ModelYes
Torch Data Typebfloat16

Best Alternatives to WoonaV1.2 9B

Best Alternatives
Context / RAM
Downloads
Likes
G2 GSHT 32K32K / 20.4 GB100
SystemGemma2 9B It32K / 18.6 GB691
Gemma 2 9B It SimPO8K / 18.6 GB26919152
Gemma 2 9B It8K / 18.6 GB540306670
Gemma 2 9B8K / 37.1 GB107376648
...2 9B Cpt Sahabatai V1 Instruct8K / 18.6 GB255234
SILMA 9B Instruct V1.08K / 18.6 GB1767968
MT Merge4 Gemma 2 9B8K / 20.4 GB1391
MT3 Gen4 Gemma 2 9B8K / 20.4 GB1084
Darkest Muse V18K / 20.4 GB20658
Note: green Score (e.g. "73.2") means that the model is better than AlexBefest/WoonaV1.2-9b.

Rank the WoonaV1.2 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? 43470 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