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

Crimson Dawn V0.1 by Epiculous

 »  All LLMs  »  Epiculous  »  Crimson Dawn V0.1   URL Share it on

  4   
  Conversational Dataset:epiculous/synthrp-gens... Dataset:epiculous/synthstruct-...   De   En   Es   Fr   It   Ja   Mistral   Pt   Region:us   Ru   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/Epiculous/Crimson_Dawn-V0.1 

Crimson Dawn V0.1 Benchmarks

LLME Score: 0.21852
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Crimson Dawn V0.1 (Epiculous/Crimson_Dawn-V0.1)

Crimson Dawn V0.1 Parameters and Internals

Model Type 
text-generation, roleplay-focused
Use Cases 
Areas:
Roleplay, Assistance
Primary Use Cases:
Engaging in personal interactions, Assistance in tasks requiring text generation
Limitations:
May not be suitable for sensitive or critical applications
Additional Notes 
The model is designed to be a personal and engaging assistant for role-playing and other text generation tasks.
Supported Languages 
en (fluent), fr (fluent), de (fluent), es (fluent), it (fluent), pt (fluent), ru (fluent), zh (fluent), ja (fluent)
Training Details 
Data Sources:
Epiculous/SynthRP-Gens-v1-Filtered-n-Cleaned, Epiculous/Synthstruct-Gens-v1-Filtered-n-Cleaned
Methodology:
Two-phased LoRA approach. Initial training on RP data followed by a second phase on instruct data.
Hardware Used:
2x NVIDIA A6000 GPUs
Model Architecture:
Fine-tuned using LoRA methodology on top of the Mistral-Nemo-Base-2407
Input Output 
Input Format:
Mistral Instruct template: ~~[INST] Prompt goes here [/INST] <\s>
Accepted Modalities:
text
Output Format:
text
LLM NameCrimson Dawn V0.1
Repository 🤗https://huggingface.co/Epiculous/Crimson_Dawn-V0.1 
Model Size12.2b
Required VRAM24.5 GB
Updated2025-01-15
MaintainerEpiculous
Model Typemistral
Model Files  4.9 GB: 1-of-5   4.9 GB: 2-of-5   4.9 GB: 3-of-5   4.9 GB: 4-of-5   4.9 GB: 5-of-5
Supported Languagesen fr de es it pt ru zh ja
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length1024000
Model Max Length1024000
Transformers Version4.44.0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<pad>
Vocabulary Size131072
Torch Data Typebfloat16

Best Alternatives to Crimson Dawn V0.1

Best Alternatives
Context / RAM
Downloads
Likes
Violet Twilight V0.21000K / 24.5 GB259522
...ish Mistral Nemo Instruct 24071000K / 24.5 GB772
Mistral Nemo Kurdish1000K / 24.5 GB412
10 14dpo1000K / 49.3 GB21091
Mistral Nemo Instruct 24071000K / 24.5 GB121707
...istralnemo DPO V7 Rp Pantsftv11000K / 24.5 GB311
...al Nemo Japanese Instruct 24081000K / 24.5 GB229230
Crimson Dawn V0.21000K / 24.5 GB2511
...l Nemo Abliterated Nemo Pro V21000K / 24.5 GB2390
Azure Dusk V0.21000K / 24.5 GB177
Note: green Score (e.g. "73.2") means that the model is better than Epiculous/Crimson_Dawn-V0.1.

Rank the Crimson Dawn V0.1 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? 41362 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