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

Sao10K L3 8B Stheno V3.1 4 25bpw EXL2 by Zoyd

 »  All LLMs  »  Zoyd  »  Sao10K L3 8B Stheno V3.1 4 25bpw EXL2   URL Share it on

  11   
  Autotrain compatible   Conversational   En   Endpoints compatible   Exl2   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/Zoyd/Sao10K_L3-8B-Stheno-v3.1-4_25bpw_exl2 

Sao10K L3 8B Stheno V3.1 4 25bpw EXL2 Benchmarks

LLME Score: 0.18775
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Sao10K L3 8B Stheno V3.1 4 25bpw EXL2 (Zoyd/Sao10K_L3-8B-Stheno-v3.1-4_25bpw_exl2)

Sao10K L3 8B Stheno V3.1 4 25bpw EXL2 Parameters and Internals

Model Type 
text generation, roleplay
Use Cases 
Areas:
Research, Commercial Applications
Applications:
1-on-1 Roleplay
Primary Use Cases:
Roleplay, RPG, Storywriting
Limitations:
Leaning towards NSFW, explicit mention required to avoid., Sometimes produces XML leaks.
Considerations:
Provide token context in the character card for best results.
Additional Notes 
Intended for roleplay, uncensored during scenarios. Occasionally produces XML leaks that can be rectified by regenerating.
Supported Languages 
en (fluent)
Training Details 
Data Sources:
outputs generated by Claude-3-Opus, Human-Generated Data
Methodology:
fine-tuning
Input Output 
Input Format:
Prompting Template - Llama-3-Instruct
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Use token context & few-shot examples for narration / RPG sessions.
Release Notes 
Version:
v3.1
Notes:
Experimental model fine-tuned based on previous learnings for an organization.
LLM NameSao10K L3 8B Stheno V3.1 4 25bpw EXL2
Repository 🤗https://huggingface.co/Zoyd/Sao10K_L3-8B-Stheno-v3.1-4_25bpw_exl2 
Model Size8b
Required VRAM5.2 GB
Updated2025-02-22
MaintainerZoyd
Model Typellama
Model Files  5.2 GB
Supported Languagesen
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-4.0
Context Length8192
Model Max Length8192
Transformers Version4.41.0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Sao10K L3 8B Stheno V3.1 4 25bpw EXL2

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 Zoyd/Sao10K_L3-8B-Stheno-v3.1-4_25bpw_exl2.

Rank the Sao10K L3 8B Stheno V3.1 4 25bpw 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