Atlantis V0.1 12B by invisietch

 »  All LLMs  »  invisietch  »  Atlantis V0.1 12B   URL Share it on

Atlantis V0.1 12B is an open-source language model by invisietch. Features: 12b LLM, VRAM: 24.5GB, Context: 1000K, License: apache-2.0, Merged, LLM Explorer Score: 0.14.

  Merged Model   Autotrain compatible   Axolotl   Conversational   En   Endpoints compatible   Mistral   Not-for-all-audiences   Qlora   Region:us   Safetensors   Sharded   Tensorflow

Atlantis V0.1 12B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Atlantis V0.1 12B Parameters and Internals

Additional Notes 
This model is built on top of Mistral's Nemo-2407-Instruct model and is a finetune aimed at improving RP/storytelling capabilities. The model may lose coherence beyond 24K context in an RP setting. It can generate explicit, disturbing, or offensive responses and should be used responsibly.
Supported Languages 
en (English)
Training Details 
Data Sources:
SicariusSicariiStuff, PJMixers, mrfakename, lodrick-the-lafted
Context Length:
128000
Hardware Used:
2x A100 80GB GPUs
Input Output 
Input Format:
Mistral prompt format
Performance Tips:
Use a low temperature setting of 0.3-0.5 to improve the model's performance.
LLM NameAtlantis V0.1 12B
Repository 🤗https://huggingface.co/invisietch/Atlantis-v0.1-12B 
Merged ModelYes
Model Size12b
Required VRAM24.5 GB
Updated2025-09-23
Maintainerinvisietch
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
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length1024000
Model Max Length1024000
Transformers Version4.43.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<pad>
Vocabulary Size131072
Torch Data Typebfloat16

Best Alternatives to Atlantis V0.1 12B

Best Alternatives
Context / RAM
Downloads
Likes
MN 12B Mag Mell R11000K / 24.5 GB69558238
Celestial Queen 12B1000K / 24.5 GB7112
MN 12B LucidFaun RP RU1000K / 24.5 GB1825
Tankie DPE 12B SFT V21000K / 24.5 GB4127
Captain Eris BMO Violent 12B1000K / 24.5 GB3052
Dans SakuraKaze V1.0.0 12B1000K / 24.5 GB4520
SauerkrautLM Nemo 12B Instruct1000K / 24.5 GB981222
...n Eris BMO Violent GRPO V0.4201000K / 24.5 GB923
...r Nemo 12B Instruct R 21 09 241000K / 24.5 GB1789139
DoublePotato Mistral Nemo 13B1000K / 26.8 GB41
Note: green Score (e.g. "73.2") means that the model is better than invisietch/Atlantis-v0.1-12B.

Rank the Atlantis V0.1 12B 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? 53999 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a