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

Mythalion Kimiko V2.6.05bpw H8 EXL2 by Eigeen

 »  All LLMs  »  Eigeen  »  Mythalion Kimiko V2.6.05bpw H8 EXL2   URL Share it on

  7   
  Autotrain compatible Dataset:oniichat/bluemoon role...   En   Exl2   Instruct   Llama   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/Eigeen/Mythalion-Kimiko-v2-6.05bpw-h8-exl2 

Mythalion Kimiko V2.6.05bpw H8 EXL2 Benchmarks

LLME Score: 0.12998
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mythalion Kimiko V2.6.05bpw H8 EXL2 (Eigeen/Mythalion-Kimiko-v2-6.05bpw-h8-exl2)

Mythalion Kimiko V2.6.05bpw H8 EXL2 Parameters and Internals

Model Type 
llama
Use Cases 
Areas:
research, commercial applications
Applications:
Roleplay scenarios
Primary Use Cases:
Roleplaying
Considerations:
Designed for RP dataset, performance in other situations not verified.
Additional Notes 
ExLlamaV2 is utilized for model quantization.
Supported Languages 
en (English)
Training Details 
Data Sources:
Oniichat/bluemoon_roleplay_chat_data_300k_messages
Methodology:
Quantization trial, RP dataset used for calibration
Context Length:
8192
LLM NameMythalion Kimiko V2.6.05bpw H8 EXL2
Repository 🤗https://huggingface.co/Eigeen/Mythalion-Kimiko-v2-6.05bpw-h8-exl2 
Model NameMythalion-Kimiko-v2
Model CreatornRuaif
Model Size13b
Required VRAM10.1 GB
Updated2025-02-22
MaintainerEigeen
Model Typellama
Instruction-BasedYes
Model Files  10.1 GB
Supported Languagesen
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.33.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Mythalion Kimiko V2.6.05bpw H8 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
CodeLlama 13B Instruct Fp1616K / 26 GB348428
...Llama 13B Instruct Hf 4bit MLX16K / 7.8 GB1002
...13B Instruct Nf4 Fp16 Upscaled16K / 26 GB1300
...B Fast Instruct 4bit Quantized4K / 7.8 GB760
Model 007 13b V24K / 26 GB264
...igogne2 Enno 13B Sft Lora 4bit4K / 26 GB7860
Xwin LM 13B V0.2 EXL24K / 5.2 GB203
Mythalion 13B 2.30bpw H4 EXL24K / 4.1 GB133
Law LLM 13B 4.0bpw H6 EXL22K / 6.8 GB51
Finance LLM 13B 6.0bpw H6 EXL22K / 10 GB41
Note: green Score (e.g. "73.2") means that the model is better than Eigeen/Mythalion-Kimiko-v2-6.05bpw-h8-exl2.

Rank the Mythalion Kimiko V2.6.05bpw H8 EXL2 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