ChatWaifu V1.2 by spow12

 ยป  All LLMs  ยป  spow12  ยป  ChatWaifu V1.2   URL Share it on

  Merged Model   Autotrain compatible   Conversational   Endpoints compatible   Ja   Mistral   Nsfw   Region:us   Roleplay   Safetensors   Sharded   Tensorflow   Visual novel
Model Card on HF ๐Ÿค—: https://huggingface.co/spow12/ChatWaifu_v1.2 

ChatWaifu V1.2 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
ChatWaifu V1.2 (spow12/ChatWaifu_v1.2)

ChatWaifu V1.2 Parameters and Internals

Model Type 
CausalLM
Use Cases 
Limitations:
May generate NSFW content due to the trained dataset.
Additional Notes 
Visual novel-based RAG is under consideration for release.
Supported Languages 
languages_supported (Japanese), language_proficiency ()
Release Notes 
Version:
1.2
Date:
2024.08.07
Notes:
Add Preference Learning in training pipeline.
Version:
1.1
Date:
2024.07.29
Notes:
Add dataset format -> generate novel, fill masked sentences. Remove system role and integrate at user message. Remove ใ€Žใ€ in conversation.
Date:
2024.06.20
Notes:
Upload other chara's sample chat history.
Date:
2024.06.13
Notes:
Upload Model
LLM NameChatWaifu V1.2
Repository ๐Ÿค—https://huggingface.co/spow12/ChatWaifu_v1.2 
Merged ModelYes
Model Size12.2b
Required VRAM24.5 GB
Updated2025-01-17
Maintainerspow12
Model Typemistral
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 Languagesja
Model ArchitectureMistralForCausalLM
Licensecc-by-nc-4.0
Context Length1024000
Model Max Length1024000
Transformers Version4.43.3
Tokenizer ClassPreTrainedTokenizerFast
Padding Token[PAD]
Vocabulary Size131073
Torch Data Typebfloat16

Best Alternatives to ChatWaifu V1.2

Best Alternatives
Context / RAM
Downloads
Likes
Violet Twilight V0.21000K / 24.5 GB255622
...ish Mistral Nemo Instruct 24071000K / 24.5 GB772
Mistral Nemo Kurdish1000K / 24.5 GB362
10 14dpo1000K / 49.3 GB20431
Mistral Nemo Instruct 24071000K / 24.5 GB125668
...al Nemo Japanese Instruct 24081000K / 24.5 GB209730
...istralnemo DPO V7 Rp Pantsftv11000K / 24.5 GB311
Crimson Dawn V0.21000K / 24.5 GB2411
...l Nemo Abliterated Nemo Pro V21000K / 24.5 GB2370
Azure Dusk V0.21000K / 24.5 GB177
Note: green Score (e.g. "73.2") means that the model is better than spow12/ChatWaifu_v1.2.

Rank the ChatWaifu V1.2 Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 41473 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227