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

MistralLite 5.0bpw H6 EXL2 by LoneStriker

 »  All LLMs  »  LoneStriker  »  MistralLite 5.0bpw H6 EXL2   URL Share it on

  17   
  Autotrain compatible   Exl2   Mistral   Pytorch   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/LoneStriker/MistralLite-5.0bpw-h6-exl2 

MistralLite 5.0bpw H6 EXL2 Benchmarks

LLME Score: 0.14715
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
MistralLite 5.0bpw H6 EXL2 (LoneStriker/MistralLite-5.0bpw-h6-exl2)

MistralLite 5.0bpw H6 EXL2 Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
research, commercial applications
Primary Use Cases:
long context line retrieval, topic retrieval, summarization, question-answering
Limitations:
Independent assessment is required to ensure compliance with quality control practices and local regulations.
Supported Languages 
English (proficient)
Training Details 
Data Sources:
SLidingEncoder and Decoder (SLED), (Long) Natural Questions (NQ), OpenAssistant Conversations Dataset (OASST1)
Methodology:
Finetuning with adapted Rotary Embedding and sliding window approach.
Context Length:
32000
Model Architecture:
Fine-tuned from Mistral-7B-v0.1
Input Output 
Input Format:
Prompt format: `<|prompter|>...~~<|assistant|>`
Accepted Modalities:
text
Output Format:
Generated text
Performance Tips:
Warm-up period required for initial inferences.
LLM NameMistralLite 5.0bpw H6 EXL2
Repository 🤗https://huggingface.co/LoneStriker/MistralLite-5.0bpw-h6-exl2 
Required VRAM4.7 GB
Updated2024-12-14
MaintainerLoneStriker
Model Typemistral
Model Files  4.7 GB
Quantization Typeexl2
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.34.0
Tokenizer ClassLlamaTokenizer
Padding Token[PAD]
Vocabulary Size32003
Torch Data Typebfloat16

Best Alternatives to MistralLite 5.0bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
NemoMix Unleashed EXL2 4bpw1000K / 7.3 GB1066
...cr To Json V1 HQQ 1bit Smashed32K / 1.6 GB190
...cr To Json V1 HQQ 4bit Smashed32K / 4.2 GB140
ScikitLLM Model EXL232K / 3 GB111
Chargen V2 8bpw EXL232K / 7.4 GB61
...tral PairRM DPO 8.0bpw H8 EXL232K / 7.4 GB82
HamSter 0.2 8.0bpw H8 EXL232K / 7.4 GB141
...N L1 Chat RL V1.6.0bpw H6 EXL232K / 5.6 GB121
...N L1 Chat RL V1.3.0bpw H6 EXL232K / 3 GB120
...Bruins V2.1.1 8.0bpw H8 EXL2 232K / 7.4 GB132
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/MistralLite-5.0bpw-h6-exl2.

Rank the MistralLite 5.0bpw H6 EXL2 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? 39237 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