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

L3.1 8B Sunfall V0.6.1 DPO by crestf411

 »  All LLMs  »  crestf411  »  L3.1 8B Sunfall V0.6.1 DPO   URL Share it on

  29   
  Autotrain compatible   Conversational   Dataset:ai-mo/numinamath-cot   Dataset:crestf411/limarp-ds   Endpoints compatible   Llama   Not-for-all-audiences   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/crestf411/L3.1-8B-sunfall-v0.6.1-dpo 

L3.1 8B Sunfall V0.6.1 DPO Benchmarks

LLME Score: 0.1882
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
L3.1 8B Sunfall V0.6.1 DPO (crestf411/L3.1-8B-sunfall-v0.6.1-dpo)

L3.1 8B Sunfall V0.6.1 DPO Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
Products requiring contextually intelligent roleplaying, Experimental storywriting
Applications:
Research in AI storytelling, Interactive story platforms
Limitations:
Early stage experimental model with unclear viability.
Additional Notes 
Trained on context mimicking Silly Tavern's Llama3-instruct preset.
Training Details 
Data Sources:
crestf411/LimaRP-DS, AI-MO/NuminaMath-CoT
Methodology:
make-it-funner-DPO merge with additional dataset expansions and rule rephrasing according to Diamond law.
Model Architecture:
Llama-3 8B Instruct modified via make-it-funner-DPO merge and fine-tuned further.
Input Output 
Input Format:
{{char}}, which is described in detail below.
Accepted Modalities:
text
Output Format:
Roleplay or story based on the given scenario
Performance Tips:
Use lore book tags with Status: Blue (constant) for optimal storytelling.
Release Notes 
Version:
v0.6.1
Date:
2024-07-31
Notes:
Major dataset expansion, enhancement of Diamond law training, unslopped SFW content integrated.
LLM NameL3.1 8B Sunfall V0.6.1 DPO
Repository 🤗https://huggingface.co/crestf411/L3.1-8B-sunfall-v0.6.1-dpo 
Model Size8b
Required VRAM16.1 GB
Updated2025-06-01
Maintainercrestf411
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
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length131072
Model Max Length131072
Transformers Version4.43.3
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to L3.1 8B Sunfall V0.6.1 DPO

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB3482107
UltraLong Thinking4192K / 16.1 GB3122
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB41815
Zero Llama 3.1 8B Beta61048K / 16.1 GB7301
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB179443
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
...xis Bookwriter Llama3.1 8B Sft1048K / 16.1 GB534
...dger Nu Llama 3.1 8B UltraLong1048K / 16.2 GB573
Note: green Score (e.g. "73.2") means that the model is better than crestf411/L3.1-8B-sunfall-v0.6.1-dpo.

Rank the L3.1 8B Sunfall V0.6.1 DPO 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? 47770 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