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

Philosophy Mistral by Heralax

 »  All LLMs  »  Heralax  »  Philosophy Mistral   URL Share it on

  139   
  Autotrain compatible Base model:heralax/philosophy-... Base model:quantized:heralax/p...   Conversational   Endpoints compatible   Generated from trainer   Ggml   Gguf   Mistral   Pytorch   Q8   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/Heralax/philosophy-mistral 

Philosophy Mistral Benchmarks

LLME Score: 0.23
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Philosophy Mistral (Heralax/philosophy-mistral)

Philosophy Mistral Parameters and Internals

Additional Notes 
This model has been trained on a narrow domain, focusing on philosophical texts from the Gutenberg project. It's very knowledgeable in this area due to memorization and uses a new dataset setting which may make it less detailed but more concise in responses. Known limitations include lack of generalist instruct data, limiting it primarily to QA.
Training Details 
Data Sources:
The Problems of Philosophy (Bertrand Russell), Beyond Good and Evil (Nietzsche), Thus Spake Zarathustra: A Book for All and None (Nietzsche), The Prince (Machiavelli), Second Treatise of Government
Methodology:
training on top 5 books on Gutenberg, new dataset setting lacking generalist instruct data
Hardware Used:
multi-GPU with 6 devices
LLM NamePhilosophy Mistral
Repository 🤗https://huggingface.co/Heralax/philosophy-mistral 
Base Model(s)  Heralax/philosophy-llm-mistral-pretrain   Heralax/philosophy-llm-mistral-pretrain
Model Size7.2b
Required VRAM7.7 GB
Updated2025-02-05
MaintainerHeralax
Model Typemistral
Model Files  14.5 GB   7.7 GB   14.5 GB
GGML QuantizationYes
GGUF QuantizationYes
Quantization Typeggml|q8|gguf
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.45.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<|end_of_text|>
Vocabulary Size32001
Torch Data Typebfloat16

Best Alternatives to Philosophy Mistral

Best Alternatives
Context / RAM
Downloads
Likes
...illHave30DolarInMyAzureAccount32K / 14.4 GB60
Mistral Kimiko CSFT32K / 14.4 GB122
Zion Alpha32K / 14.4 GB28443
LCARS AI 00132K / 14.4 GB144
Mixtral Quantized32K / 14.4 GB110
Mayonnaise 4in1 0232K / 14.4 GB900
Zsql En Postgres32K / 14.4 GB645
MHENNlitv332K / 28.9 GB90
MHENNlitv232K / 28.9 GB90
MHENNcodemathv232K / 28.9 GB80
Note: green Score (e.g. "73.2") means that the model is better than Heralax/philosophy-mistral.

Rank the Philosophy Mistral 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? 42577 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