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

Mistral Trismegistus 7B GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Mistral Trismegistus 7B GPTQ   URL Share it on

  24   5
  4-bit   Autotrain compatible Base model:quantized:teknium/m... Base model:teknium/mistral-tri...   Distillation   En   Finetuned   Gpt4   Gptq   Instruct   Mistral   Mistral-7b   Quantized   Region:us   Safetensors   Synthetic data
Model Card on HF 🤗: https://huggingface.co/TheBloke/Mistral-Trismegistus-7B-GPTQ 

Mistral Trismegistus 7B GPTQ Benchmarks

LLME Score: 0.13294
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Sponsored by Nebius

Mistral Trismegistus 7B GPTQ Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
esoteric, occult, spiritual
Applications:
chatbots for spiritual guidance, hypnosis simulations
Primary Use Cases:
Answering questions about occult artifacts, Playing the role of a hypnotist
Limitations:
Limited to esoteric and spiritual topics
Additional Notes 
This model is tuned for creative and esoteric tasks, emphasizing depth and richness in the occult.
Supported Languages 
en (fluent)
Training Details 
Data Sources:
GPT-4 generated dataset
Data Volume:
35,000 examples
Methodology:
Synthetic data generation, fine-tuning
Model Architecture:
Mistral architecture
Input Output 
Input Format:
USER: {prompt} ASSISTANT:
Accepted Modalities:
text
Output Format:
text
LLM NameMistral Trismegistus 7B GPTQ
Repository 🤗https://huggingface.co/TheBloke/Mistral-Trismegistus-7B-GPTQ 
Model NameMistral Trismegistus 7B
Model CreatorTeknium
Base Model(s)  Mistral Trismegistus 7B   teknium/Mistral-Trismegistus-7B
Model Size7b
Required VRAM4.2 GB
Updated2025-03-14
MaintainerTheBloke
Model Typemistral
Model Files  4.2 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.34.0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Mistral Trismegistus 7B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Mistral 7B Instruct V0.3 GPTQ32K / 4.2 GB3264660
...ephyr 7B Beta Channelwise Gptq32K / 4 GB121030
...ral 7B Instruct V0.3 GPTQ 4bit32K / 4.2 GB107818
Mistral 7B Instruct V0.2 GPTQ32K / 4.2 GB1431950
...stral 7B Instruct V0.3 GPTQ 8B32K / 7.7 GB2601
...istral 7B Pruned50 GPTQ Marlin32K / 4 GB60
Mistral 7B Unsloth Gptq 8bit32K / 7.7 GB60
Mistral 7B OpenOrca GPTQ32K / 4.2 GB19332100
...lai Mistral 7B V0.1 4 Bit Gptq32K / 4.2 GB240
...phyr 7B Beta Assistant V1 Gptq32K / 4.2 GB91
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Mistral-Trismegistus-7B-GPTQ.

Rank the Mistral Trismegistus 7B GPTQ 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? 45019 in total.

This website uses cookies and Google Analytics. Both remember your actions and preferences for a better online experience on the website. By continuing to use the website, you agree to our Privacy Policy.
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