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

SciPhi Mistral 7B 32K AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  SciPhi Mistral 7B 32K AWQ   URL Share it on

  7   
  Arxiv:2301.13688   Arxiv:2306.02707   4-bit   Autotrain compatible   Awq Base model:quantized:sciphi/sc... Base model:sciphi/sciphi-mistr...   Mistral   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/SciPhi-Mistral-7B-32k-AWQ 

SciPhi Mistral 7B 32K AWQ Benchmarks

LLME Score: 0.11788
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
SciPhi Mistral 7B 32K AWQ (TheBloke/SciPhi-Mistral-7B-32k-AWQ)
🌟 Advertise your project 🚀

SciPhi Mistral 7B 32K AWQ Parameters and Internals

Model Type 
mistral
Additional Notes 
Model was quantized by TheBloke using AWQ method for faster Transformers-based inference. Supports 4-bit quantization.
Training Details 
Data Sources:
regular instruction tuning data, synthetic textbooks
Data Volume:
more than 1 billion tokens
Methodology:
fine-tuning process over four epochs
Model Architecture:
Transformer-based model with features like Grouped-Query Attention and Sliding-Window Attention
LLM NameSciPhi Mistral 7B 32K AWQ
Repository 🤗https://huggingface.co/TheBloke/SciPhi-Mistral-7B-32k-AWQ 
Model NameSciPhi Mistral 7B 32K
Model CreatorSciPhi
Base Model(s)  SciPhi Mistral 7B 32K   SciPhi/SciPhi-Mistral-7B-32k
Model Size7b
Required VRAM4.2 GB
Updated2025-09-13
MaintainerTheBloke
Model Typemistral
Model Files  4.2 GB
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureMistralForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.34.1
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to SciPhi Mistral 7B 32K AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Mistral 7B Instruct V0.2 AWQ32K / 4.2 GB60
Mistral 7B Instruct V0.3 AWQ32K / 4.2 GB48385
Mistral 7B Instruct V0.2 AWQ32K / 4.2 GB2661049
Ghost 7B Alpha AWQ32K / 4.2 GB60
Tess 7B V2.0 AWQ32K / 4.2 GB31
...reeze 7B 32K Instruct V1.0 AWQ32K / 4.7 GB90
Breeze 7B Instruct V1.0 AWQ32K / 4.6 GB60
Mahou 1.3a Mistral 7B AWQ32K / 4.2 GB71
Mahou 1.3 Mistral 7B AWQ32K / 4.2 GB80
NSFW DPO Noromaid 7B AWQ32K / 4.2 GB301
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/SciPhi-Mistral-7B-32k-AWQ.

Rank the SciPhi Mistral 7B 32K AWQ 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? 51352 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 v20241124
  Support LLM Explorer