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

EtherealRainbow V0.2 8B EXL2 8BPW by Statuo

 »  All LLMs  »  Statuo  »  EtherealRainbow V0.2 8B EXL2 8BPW   URL Share it on

  10   
  8-bit   Autotrain compatible   Conversational   Endpoints compatible   Exl2   Llama   Merge   Mergekit   Not-for-all-audiences   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/Statuo/EtherealRainbow-v0.2-8B_EXL2_8BPW 

EtherealRainbow V0.2 8B EXL2 8BPW Benchmarks

LLME Score: 0.19283
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
EtherealRainbow V0.2 8B EXL2 8BPW (Statuo/EtherealRainbow-v0.2-8B_EXL2_8BPW)

EtherealRainbow V0.2 8B EXL2 8BPW Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
creative writing, roleplay
Limitations:
Known to generate explicit, disturbing, or offensive responses.
Additional Notes 
The model may require editing the first 2-3 responses to set the desired roleplay style. Temperatures common for other models might be too high for EtherealRainbow.
Training Details 
Methodology:
EtherealRainbow is a two-stage merge. Rain is created using `dare_ties` from selected Llama3-based models, and Sun is created similarly to enhance creative writing and anatomical knowledge. Finally, Rain and Sun are merged using `slerp`.
Input Output 
Input Format:
Llama-3 Instruct prompting format
Accepted Modalities:
text
Output Format:
bf16 Safetensors & various GGUF quantizations
Performance Tips:
Runs 'hot' by default, recommend starting with temperature 0.7 and adjusting as needed.
LLM NameEtherealRainbow V0.2 8B EXL2 8BPW
Repository 🤗https://huggingface.co/Statuo/EtherealRainbow-v0.2-8B_EXL2_8BPW 
Model Size8b
Required VRAM8.6 GB
Updated2025-02-22
MaintainerStatuo
Model Typellama
Model Files  8.6 GB
Supported Languagesen
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.41.2
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to EtherealRainbow V0.2 8B EXL2 8BPW

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 Statuo/EtherealRainbow-v0.2-8B_EXL2_8BPW.

Rank the EtherealRainbow V0.2 8B EXL2 8BPW 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