thumbnail: >-
https://huggingface.co/PocketDoc/Dans-PersonalityEngine-V1.3.0-24b/resolve/main/resources/pe.png
license: apache-2.0
tags:
- general-purpose
- roleplay
- storywriting
- chemistry
- biology
- code
- climate
- axolotl
- text-generation-inference
- finetune
- legal
- medical
- finance
datasets:
- PocketDoc/Dans-Prosemaxx-RP
- PocketDoc/Dans-Personamaxx-Logs-2
- PocketDoc/Dans-Personamaxx-VN
- PocketDoc/Dans-Kinomaxx-VanillaBackrooms
- PocketDoc/Dans-Prosemaxx-Gutenberg
- PocketDoc/Dans-Prosemaxx-Cowriter-3-XL
- PocketDoc/Dans-Prosemaxx-Adventure
- PocketDoc/Dans-Failuremaxx-Adventure-3
- PocketDoc/Dans-Prosemaxx-InstructWriter-ZeroShot-2
- PocketDoc/Dans-Prosemaxx-InstructWriter-ZeroShot-3
- PocketDoc/Dans-Prosemaxx-InstructWriter-Continue-2
- PocketDoc/Dans-Prosemaxx-Instructwriter-Long
- PocketDoc/Dans-Prosemaxx-RepRemover-1
- PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
- AquaV/US-Army-Survival-Sharegpt
- AquaV/Multi-Environment-Operations-Sharegpt
- AquaV/Resistance-Sharegpt
- AquaV/Interrogation-Sharegpt
- AquaV/Chemical-Biological-Safety-Applications-Sharegpt
- AquaV/Energetic-Materials-Sharegpt
- PocketDoc/Dans-Mathmaxx
- PJMixers/Math-Multiturn-1K-ShareGPT
- PocketDoc/Dans-Taskmaxx
- PocketDoc/Dans-Taskmaxx-DataPrepper
- PocketDoc/Dans-Taskmaxx-ConcurrentQA-Reworked
- PocketDoc/Dans-Taskmaxx-TableGPT
- PocketDoc/Dans-Taskmaxx-SciRIFF
- PocketDoc/Dans-Taskmaxx-Edit
- PocketDoc/Dans-Toolmaxx-Agent
- PocketDoc/Dans-Toolmaxx-ShellCommands
- PocketDoc/Dans-Toolmaxx-Functions-Toolbench
- PocketDoc/Dans-Toolmaxx-Functions-ToolACE
- PocketDoc/Dans-Toolmaxx-Functions-apigen-subset
- PocketDoc/Dans-Assistantmaxx-OpenAssistant2
- PocketDoc/Dans-Assistantmaxx-Opus-Merge-2
- PocketDoc/Dans-Assistantmaxx-sonnetorca-subset
- PocketDoc/Dans-Assistantmaxx-sonnetorca-subset-2
- PocketDoc/Dans-Assistantmaxx-Synthia
- PocketDoc/Dans-Assistantmaxx-ASL
- PocketDoc/Dans-Assistantmaxx-PersonaLLM-Opus
- PocketDoc/Dans-Assistantmaxx-LongAlign
- PocketDoc/Dans-Assistantmaxx-OpenLeecher-Instruct
- PocketDoc/Dans-Assistantmaxx-Tulu3-IF
- PocketDoc/Dans-Systemmaxx
- PocketDoc/Dans-Logicmaxx-SAT-AP
- PJMixers/grimulkan_theory-of-mind-ShareGPT
- PJMixers/grimulkan_physical-reasoning-ShareGPT
- PocketDoc/Dans-Reasoningmaxx-NaturalReasoning
- PocketDoc/Dans-Reasoningmaxx-WebInstruct
- PocketDoc/Dans-Reasoningmaxx-GeneralReasoning
- PocketDoc/Dans-Assistantmaxx-ClosedInstruct
language:
- en
base_model:
- mistralai/Mistral-Small-3.1-24B-Base-2503
pipeline_tag: text-generation
library_name: transformers
Dans-PersonalityEngine-V1.3.0-24b
Dans-PersonalityEngine is a versatile model series designed for exceptional performance across a wide range of tasks and domains.
This model series has been meticulously fine-tuned on a diverse corpus of 40+ specialized datasets to excel at both creative endeavors like roleplay and co-writing, and technical tasks such as code generation, tool use, and complex reasoning.
The total dataset size is around 1.7B tokens, 1.1B of which are creative and 600M are technical.
V1.3.0 introduces multilingual capabilities with support for 10 languages and enhanced domain expertise across multiple fields.
Multilingual Support
Arabic Chinese English French German Hindi Japanese Korean Portuguese Spanish
Key Details
BASE MODEL: mistralai/Mistral-Small-3.1-24B-Base-2503 LICENSE: apache-2.0 LANGUAGE: Multilingual with 10 supported languages CONTEXT LENGTH: 32768 tokens, 131072 with degraded performance
Recommended Settings
TEMPERATURE: 1.0 TOP_P: 0.95 MIN_P: 0.05
Prompting Format
The model uses the following format I'll refer to as "DanChat-2":
<|system|>system prompt<|endoftext|><|user|>Hi there!<|endoftext|><|assistant|>Hey, how can I help?<|endoftext|>
SillyTavern Template
Training Process
The model was trained using Axolotl on 8x H100 GPUs for 50 hours.
Support Development
Development is limited by funding and resources. To help support:
- Contact on HF
- Email: [email protected]
