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

Dans PersonalityEngine V1.0.0 8B by PocketDoc

 »  All LLMs  »  PocketDoc  »  Dans PersonalityEngine V1.0.0 8B   URL Share it on

  23   
Base model:dans-discountmodels... Base model:finetune:dans-disco...   Biology   Chemistry   Climate   Code   Conversational Dataset:aquav/chemical-biologi... Dataset:aquav/energetic-materi... Dataset:aquav/interrogation-sh... Dataset:aquav/multi-environmen... Dataset:aquav/resistance-share... Dataset:aquav/us-army-survival... Dataset:pjmixers/math-multitur... Dataset:pocketdoc/dans-asciima... Dataset:pocketdoc/dans-assista... Dataset:pocketdoc/dans-assista... Dataset:pocketdoc/dans-assista... Dataset:pocketdoc/dans-assista... Dataset:pocketdoc/dans-assista... Dataset:pocketdoc/dans-assista... Dataset:pocketdoc/dans-benchma... Dataset:pocketdoc/dans-codemax... Dataset:pocketdoc/dans-codemax... Dataset:pocketdoc/dans-codemax... Dataset:pocketdoc/dans-logicma... Dataset:pocketdoc/dans-mathmax... Dataset:pocketdoc/dans-memoryc... Dataset:pocketdoc/dans-persona... Dataset:pocketdoc/dans-prosema... Dataset:pocketdoc/dans-prosema... Dataset:pocketdoc/dans-prosema... Dataset:pocketdoc/dans-prosema... Dataset:pocketdoc/dans-systemm... Dataset:pocketdoc/dans-taskmax... Dataset:pocketdoc/dans-taskmax... Dataset:pocketdoc/dans-taskmax... Dataset:pocketdoc/dans-toolmax... Dataset:pocketdoc/dans-toolmax...   Dataset:pocketdoc/danstestyard   En   Instruct   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/PocketDoc/Dans-PersonalityEngine-v1.0.0-8b 

Dans PersonalityEngine V1.0.0 8B Benchmarks

MMLU Pro: 22.95
GPQA: 4.7
MUSR: 3.94
BBH: 25.69
IFEval: 49.82 vs 88 (so35)-43.4%
MATH Lvl 5: 8.16
LLME Score: 0.27599
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Dans PersonalityEngine V1.0.0 8B (PocketDoc/Dans-PersonalityEngine-v1.0.0-8b)

Dans PersonalityEngine V1.0.0 8B Parameters and Internals

Model Type 
text generation
Use Cases 
Limitations:
No harmfulness alignment.
Supported Languages 
en (full)
Training Details 
Data Sources:
PocketDoc/Dans-MemoryCore-CoreCurriculum-Small, PocketDoc/Dans-Prosemaxx-Gutenberg, PocketDoc/Dans-Prosemaxx-Cowriter-S, PocketDoc/Dans-Prosemaxx-Adventure, PocketDoc/Dans-Prosemaxx-Opus-Writing, PocketDoc/Dans-Assistantmaxx-Sharegpt, PocketDoc/Dans-Assistantmaxx-OpenAssistant2, PocketDoc/Dans-Assistantmaxx-Opus-instruct-1, PocketDoc/Dans-Assistantmaxx-Opus-instruct-2, PocketDoc/Dans-Assistantmaxx-Opus-instruct-3, PocketDoc/Dans-Assistantmaxx-Opus-Multi-Instruct, PocketDoc/Dans-Assistantmaxx-sonnetorca-subset, PocketDoc/Dans-Assistantmaxx-NoRobots, AquaV/Energetic-Materials-Sharegpt, AquaV/Chemical-Biological-Safety-Applications-Sharegpt, AquaV/US-Army-Survival-Sharegpt, AquaV/Resistance-Sharegpt, AquaV/Interrogation-Sharegpt, AquaV/Multi-Environment-Operations-Sharegpt, PocketDoc/Dans-Mathmaxx, PJMixers/Math-Multiturn-1K-ShareGPT, PocketDoc/Dans-Benchmaxx, PocketDoc/Dans-Codemaxx-LeetCode, PocketDoc/Dans-Codemaxx-CodeFeedback-Conversations, PocketDoc/Dans-Codemaxx-CodeFeedback-SingleTurn, PocketDoc/Dans-Taskmaxx, PocketDoc/Dans-Taskmaxx-DataPrepper, PocketDoc/Dans-Taskmaxx-ConcurrentQA-Reworked, PocketDoc/Dans-Systemmaxx, PocketDoc/Dans-Toolmaxx-Agent, PocketDoc/Dans-Toolmaxx-ShellCommands, PocketDoc/Dans-ASCIIMaxx-Wordart, PocketDoc/Dans-Personamaxx, PocketDoc/DansTestYard, PocketDoc/Dans-Logicmaxx-Skunkworks
Methodology:
Full finetuned for 4 epochs
Training Time:
21 hours
Hardware Used:
8x H100
Input Output 
Input Format:
ChatML format prompting
Accepted Modalities:
text
LLM NameDans PersonalityEngine V1.0.0 8B
Repository 🤗https://huggingface.co/PocketDoc/Dans-PersonalityEngine-v1.0.0-8b 
Base Model(s)  meta-llama/Llama-3.1-8B   Dans-DiscountModels/Meta-Llama-3.1-8B-ChatML   meta-llama/Llama-3.1-8B   Dans-DiscountModels/Meta-Llama-3.1-8B-ChatML
Model Size8b
Required VRAM16.1 GB
Updated2025-02-22
MaintainerPocketDoc
Model Typellama
Instruction-BasedYes
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
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.45.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|finetune_right_pad_id|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Dans PersonalityEngine V1.0.0 8B

Best Alternatives
Context / RAM
Downloads
Likes
...a 3 8B Instruct Gradient 1048K1024K / 16.1 GB3927680
Mpasila Viking 8B1024K / 16.1 GB840
Hel V2 8B DARK FICTION1024K / 16.1 GB220
161024K / 16.1 GB1690
...di95 LewdStorytellerMix 8B 64K1024K / 16.1 GB692
Because Im Bored Nsfw11024K / 16.1 GB361
121024K / 16.1 GB600
MrRoboto ProLong 8B V4b1024K / 16.1 GB1070
MrRoboto ProLong 8B V1a1024K / 16.1 GB1080
MrRoboto ProLong 8B V2a1024K / 16.1 GB1020
Note: green Score (e.g. "73.2") means that the model is better than PocketDoc/Dans-PersonalityEngine-v1.0.0-8b.

Rank the Dans PersonalityEngine V1.0.0 8B 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? 43470 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