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

Llama 3 Natsuki Ddlc 8B V1 by 922-CA

 »  All LLMs  »  922-CA  »  Llama 3 Natsuki Ddlc 8B V1   URL Share it on

  11   
  4bit   Autotrain compatible Base model:finetune:unsloth/ll... Base model:unsloth/llama-3-8b-...   Dataset:922-ca/nacha v1   En   Endpoints compatible   Llama   Model-index   Pytorch   Quantized   Region:us   Sharded   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/922-CA/Llama-3-natsuki-ddlc-8b-v1 

Llama 3 Natsuki Ddlc 8B V1 Benchmarks

ARC: 60.32 vs 96.7 (so35)-37.6%
HellaSwag: 80.99 vs 95.3 (gpt4)-15%
MMLU: 64.75 vs 88.3 (so35)-26.7%
TruthfulQA: 45.41 vs 59 (gpt4)-23%
WinoGrande: 78.77 vs 87.5 (gpt4)-10%
GSM8K: 41.85 vs 96.4 (so35)-56.6%
LLME Score: 0.20356
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3 Natsuki Ddlc 8B V1 (922-CA/Llama-3-natsuki-ddlc-8b-v1)

Llama 3 Natsuki Ddlc 8B V1 Parameters and Internals

Model Type 
text-generation
Additional Notes 
This model is fine-tuned for the Natsuki character from the DDLC game. It is designed to emulate her personality closely and may generate outputs that might not align with reality. Use at your own risk.
Training Details 
Data Sources:
922-CA/NaChA_v1
Methodology:
LoRA (Low-Rank Adaptation)
Model Architecture:
LoRA architecture with rank: 32, lora alpha: 32, trained for 1 epoch, learning rate: 2e-4, batch size: 2, grad steps: 4.
LLM NameLlama 3 Natsuki Ddlc 8B V1
Repository 🤗https://huggingface.co/922-CA/Llama-3-natsuki-ddlc-8b-v1 
Base Model(s)  Llama 3 8B Bnb 4bit   unsloth/llama-3-8b-bnb-4bit
Model Size8b
Required VRAM16.1 GB
Updated2025-02-22
Maintainer922-CA
Model Typellama
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.2 GB: 4-of-4
Supported Languagesen
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.40.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|reserved_special_token_250|>
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Llama 3 Natsuki Ddlc 8B V1

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 4bit1024K / 4.5 GB212
...B Instruct Gradient 1048K 8bit1024K / 8.6 GB71
...truct Gradient 1048K Bpw6 EXL21024K / 6.7 GB102
...truct Gradient 1048K Bpw5 EXL21024K / 5.8 GB70
Llama 3 8B Instruct 1048K 4bit1024K / 4.5 GB1225
Llama 3 8B Instruct 1048K 8bit1024K / 8.6 GB2817
... Gradient 1048K 8.0bpw H8 EXL21024K / 8.6 GB83
...ct Gradient 1048K Bpw2.25 EXL21024K / 3.4 GB51
Llama 3 8B Instruct 262K 2bit256K / 2.5 GB71
...B Instruct 262k V2 EXL2 6.0bpw256K / 6.7 GB111
Note: green Score (e.g. "73.2") means that the model is better than 922-CA/Llama-3-natsuki-ddlc-8b-v1.

Rank the Llama 3 Natsuki Ddlc 8B V1 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