Rocinante 12B V1 by TheDrummer

 ยป  All LLMs  ยป  TheDrummer  ยป  Rocinante 12B V1   URL Share it on

  Mistral   Region:us   Safetensors   Sharded   Tensorflow

Rocinante 12B V1 Benchmarks

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

Rocinante 12B V1 Parameters and Internals

Model Type
text generation, storytelling, adventure
Use Cases
Areas:
research, commercial applications
Applications:
adventure stories, role-playing
Primary Use Cases:
storytelling, instruction-based storytelling
Additional NotesThe model provides enriched prose, creative outputs, and adventure-filled storytelling capabilities.
Input Output
Performance Tips:Sampler suggestions: Temp 0.7 for a chill experience, Temp 1.2 for a more intense experience.
LLM NameRocinante 12B V1
Repository ๐Ÿค—https://huggingface.co/TheDrummer/Rocinante-12B-v1 
Model Size12b
Required VRAM24.5 GB
Updated2024-11-13
MaintainerTheDrummer
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   0.0 GB
Model ArchitectureMistralForCausalLM
Licenseother
Context Length1024000
Model Max Length1024000
Transformers Version4.44.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<pad>
Vocabulary Size131072
Torch Data Typebfloat16
Rocinante 12B V1 (TheDrummer/Rocinante-12B-v1)

Best Alternatives to Rocinante 12B V1

Best Alternatives
Context / RAM
Downloads
Likes
Magnum V4 12B1000K / 24.5 GB83823
Dolphin 2.9.3 Mistral Nemo 12B1000K / 24.5 GB698283
SauerkrautLM Nemo 12B Instruct1000K / 24.5 GB850721
Mini Magnum 12B V1.11000K / 24.5 GB496669
...r Nemo 12B Instruct R 21 09 241000K / 24.5 GB1504281
ChatWaifu 12B V2.01000K / 24.5 GB25510
Starcannon Unleashed 12B V1.01000K / 24.5 GB81425
Saiga Nemo 12b1000K / 24.5 GB473213
Romulus Mistral Nemo 12B Simpo1000K / 24.5 GB369615
NemoMix Unleashed 12B1000K / 24.5 GB10435143
Note: green Score (e.g. "73.2") means that the model is better than TheDrummer/Rocinante-12B-v1.

Rank the Rocinante 12B V1 Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 37901 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110