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

Hamanasu 4B Instruct KTO V2 by Delta-Vector

 »  All LLMs  »  Delta-Vector  »  Hamanasu 4B Instruct KTO V2   URL Share it on

  3   
Base model:delta-vector/hamana... Base model:finetune:delta-vect... Dataset:neweden/kto-instruct-m... Dataset:neweden/opus-accepted-...   Finetuned   Instruct   Llama   Region:us   Roleplay   Safetensors   Sharded   Storywriting   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Delta-Vector/Hamanasu-4B-Instruct-KTO-V2 

Hamanasu 4B Instruct KTO V2 Benchmarks

LLME Score: 0.21144
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Hamanasu 4B Instruct KTO V2 (Delta-Vector/Hamanasu-4B-Instruct-KTO-V2)
🌟 Advertise your project 🚀

Hamanasu 4B Instruct KTO V2 Parameters and Internals

LLM NameHamanasu 4B Instruct KTO V2
Repository 🤗https://huggingface.co/Delta-Vector/Hamanasu-4B-Instruct-KTO-V2 
Base Model(s)  Hamanasu 4B Instruct KTO V1   Delta-Vector/Hamanasu-4B-Instruct-KTO-V1
Model Size4b
Required VRAM9 GB
Updated2025-10-11
MaintainerDelta-Vector
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   4.0 GB: 2-of-2   0.0 GB   0.0 GB
Model ArchitectureLlamaForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.50.0
Tokenizer ClassPreTrainedTokenizer
Padding Token<|finetune_right_pad_id|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Hamanasu 4B Instruct KTO V2

Best Alternatives
Context / RAM
Downloads
Likes
HoldMy4BKTO256K / 8.8 GB50
Xgen Small 4B Instruct R256K / 17.7 GB183
Aura 4B128K / 9 GB2813
Hamanasu Magnum 4B128K / 9 GB94
Hamanasu Adventure 4B128K / 9.1 GB64
Hamanasu 4B Chat Brainrot128K / 9 GB93
Hamanasu 4B Instruct KTO V1128K / 9 GB72
4B Inst128K / 9 GB160
Hamanasu 4B Instruct128K / 9 GB02
4B Inst128K / 9 GB60
Note: green Score (e.g. "73.2") means that the model is better than Delta-Vector/Hamanasu-4B-Instruct-KTO-V2.

Rank the Hamanasu 4B Instruct KTO 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? 51545 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