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

ChatWaifu V1.3.1 by spow12

 »  All LLMs  »  spow12  »  ChatWaifu V1.3.1   URL Share it on

  12   
  Autotrain compatible Base model:epiculous/violet tw... Base model:merge:epiculous/vio... Base model:merge:mistralai/mis... Base model:merge:neversleep/lu... Base model:merge:spow12/chatwa... Base model:mistralai/mistral-n... Base model:neversleep/lumimaid... Base model:spow12/chatwaifu v1...   Conversational   De   En   Endpoints compatible   Es   Fr   Instruct   It   Ja   Merge   Mergekit   Mistral   Nsfw   Pt   Region:us   Roleplay   Ru   Safetensors   Sharded   Tensorflow   Visual novel   Zh
Model Card on HF 🤗: https://huggingface.co/spow12/ChatWaifu_v1.3.1 

ChatWaifu V1.3.1 Benchmarks

LLME Score: 0.17236
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
ChatWaifu V1.3.1 (spow12/ChatWaifu_v1.3.1)
🌟 Advertise your project 🚀

ChatWaifu V1.3.1 Parameters and Internals

Model Type 
CausalLM, text-generation
Use Cases 
Areas:
Research, Non-commercial applications
Applications:
Visual novel roleplay, AI assistants, Custom character generation
Primary Use Cases:
Fluent chat performance, Zero shot character persona generation
Limitations:
The model may generate NSFW content, Limited to visual novel character implementation
Considerations:
Use responsibly in a manner that respects the licensing terms.
Additional Notes 
This model supports long multiturn conversation and is tailored for visual novel characters.
Supported Languages 
en (some proficiency), fr (some proficiency), de (some proficiency), es (some proficiency), it (some proficiency), pt (some proficiency), ru (some proficiency), zh (some proficiency), ja (full proficiency)
Training Details 
Methodology:
Merge using mergekit
Context Length:
131072
Safety Evaluation 
Ethical Considerations:
This model may generate NSFW content.
Release Notes 
Version:
1.3.1
Date:
2024-08-29
Notes:
Merged Ver1.2, Mistral-Nemo-Instruct-2407, NeverSleep/Lumimaid-v0.2-12B, Epiculous/Violet_Twilight-v0.1. Adjusted merge weight.
Version:
1.3
Date:
2024-08-16
Notes:
Merged Ver1.2, Mistral-Nemo-Instruct-2407, NeverSleep/Lumimaid-v0.2-12B.
Version:
1.2.1
Date:
2024-08-08
Notes:
Merged Ver1.2 and Mistral-Nemo-Instruct-2407.
Version:
1.2
Date:
2024-08-07
Notes:
Added Preference Learning in training pipeline.
LLM NameChatWaifu V1.3.1
Repository 🤗https://huggingface.co/spow12/ChatWaifu_v1.3.1 
Base Model(s)  spow12/ChatWaifu_v1.2   Mistral Nemo Instruct 2407   NeverSleep/Lumimaid-v0.2-12B   Epiculous/Violet_Twilight-v0.1   spow12/ChatWaifu_v1.2   mistralai/Mistral-Nemo-Instruct-2407   NeverSleep/Lumimaid-v0.2-12B   Epiculous/Violet_Twilight-v0.1
Model Size12.2b
Required VRAM24.5 GB
Updated2025-09-23
Maintainerspow12
Model Typemistral
Instruction-BasedYes
Model Files  4.9 GB: 1-of-5   4.9 GB: 2-of-5   4.9 GB: 3-of-5   4.9 GB: 4-of-5   4.9 GB: 5-of-5
Supported Languagesen fr de es it pt ru zh ja
Model ArchitectureMistralForCausalLM
Licensecc-by-nc-4.0
Context Length1024000
Model Max Length1024000
Transformers Version4.44.2
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size131072
Torch Data Typebfloat16

Best Alternatives to ChatWaifu V1.3.1

Best Alternatives
Context / RAM
Downloads
Likes
...ish Mistral Nemo Instruct 24071000K / 24.5 GB772
10 14dpo1000K / 49.3 GB215323
Violet Twilight V0.21000K / 24.5 GB15944
Mistral Nemo Kurdish1000K / 24.5 GB13
Kalypso1000K / 24.5 GB419
Crimson Dawn V0.21000K / 24.5 GB6114
Azure Dusk V0.21000K / 24.5 GB9710
Educa Ai Nemo Sft1000K / 49.3 GB44
...al Nemo Japanese Instruct 24081000K / 24.5 GB59445
...l Nemo Abliterated Nemo Pro V21000K / 24.5 GB130
Note: green Score (e.g. "73.2") means that the model is better than spow12/ChatWaifu_v1.3.1.

Rank the ChatWaifu V1.3.1 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? 51566 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 v20241124
  Support LLM Explorer