Mistral Trismegistus 7B AWQ by TheBloke

 ยป  All LLMs  ยป  TheBloke  ยป  Mistral Trismegistus 7B AWQ   URL Share it on

  4-bit   Autotrain compatible   Awq Base model:quantized:teknium/m... Base model:teknium/mistral-tri...   Distillation   En   Finetuned   Gpt4   Instruct   Mistral   Mistral-7b   Quantized   Region:us   Safetensors   Synthetic data

Mistral Trismegistus 7B AWQ Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mistral Trismegistus 7B AWQ (TheBloke/Mistral-Trismegistus-7B-AWQ)

Mistral Trismegistus 7B AWQ Parameters and Internals

Model Type 
mistral
Use Cases 
Areas:
Research, Personal exploration of esoteric, occult, and spiritual topics
Applications:
Educational tools, Content creation in niche topics
Limitations:
Not a replacement for professional spiritual guidance
Additional Notes 
This model is intended for those interested in non-mainstream topics, emphasizing creative and esoteric knowledge.
Supported Languages 
en (high)
Training Details 
Data Sources:
100% synthetic, gpt-4 generated dataset
Data Volume:
35,000 examples
Methodology:
Training on a diverse set of tasks related to esoteric, occult, and spiritual topics
Input Output 
Input Format:
USER: {prompt}
Accepted Modalities:
text
Output Format:
ASSISTANT: {response}
LLM NameMistral Trismegistus 7B AWQ
Repository ๐Ÿค—https://huggingface.co/TheBloke/Mistral-Trismegistus-7B-AWQ 
Model NameMistral Trismegistus 7B
Model CreatorTeknium
Base Model(s)  Mistral Trismegistus 7B   teknium/Mistral-Trismegistus-7B
Model Size7b
Required VRAM4.2 GB
Updated2025-02-05
MaintainerTheBloke
Model Typemistral
Model Files  4.2 GB
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
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 AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Mistral 7B Instruct V0.2 AWQ32K / 4.2 GB60
Mistral 7B Instruct V0.3 AWQ32K / 4.2 GB35422
Mistral 7B Instruct V0.2 AWQ32K / 4.2 GB4751043
Ghost 7B Alpha AWQ32K / 4.2 GB780
Breeze 7B Instruct V1.0 AWQ32K / 4.6 GB800
Mahou 1.3a Mistral 7B AWQ32K / 4.2 GB761
Tess 7B V2.0 AWQ32K / 4.2 GB771
Mahou 1.3 Mistral 7B AWQ32K / 4.2 GB770
...reeze 7B 32K Instruct V1.0 AWQ32K / 4.7 GB90
...Instruct V0.2 AWQ 4bit Smashed32K / 4.2 GB771
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Mistral-Trismegistus-7B-AWQ.

Rank the Mistral Trismegistus 7B AWQ 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? 42577 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227