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

Smaugv0.1 4.65bpw H6 EXL2 by LoneStriker

 »  All LLMs  »  LoneStriker  »  Smaugv0.1 4.65bpw H6 EXL2   URL Share it on

  14   
  Merged Model   Autotrain compatible Base model:finetune:mistralai/... Base model:mistralai/mistral-7...   Conversational   Endpoints compatible   Exl2   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/LoneStriker/Smaugv0.1-4.65bpw-h6-exl2 

Smaugv0.1 4.65bpw H6 EXL2 Benchmarks

LLME Score: 0.17048
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Smaugv0.1 4.65bpw H6 EXL2 (LoneStriker/Smaugv0.1-4.65bpw-h6-exl2)

Smaugv0.1 4.65bpw H6 EXL2 Parameters and Internals

Additional Notes 
This model is a fine-tune of jondurbin's excellent model and will have shared new datasets and techniques with the community soon.
Training Details 
Data Sources:
jondurbin/bagel
Methodology:
new technique
LLM NameSmaugv0.1 4.65bpw H6 EXL2
Repository 🤗https://huggingface.co/LoneStriker/Smaugv0.1-4.65bpw-h6-exl2 
Base Model(s)  mistralai/Mistral-7B-v0.1   mistralai/Mistral-7B-v0.1
Merged ModelYes
Model Size7b
Required VRAM20.8 GB
Updated2024-12-21
MaintainerLoneStriker
Model Typellama
Model Files  8.6 GB: 1-of-3   8.6 GB: 2-of-3   3.6 GB: 3-of-3
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length200000
Model Max Length200000
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size64000
Torch Data Typebfloat16

Best Alternatives to Smaugv0.1 4.65bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
Smaugv0.1 6.0bpw H6 EXL2195K / 26.4 GB144
Smaugv0.1 5.0bpw H6 EXL2195K / 22.3 GB143
Smaugv0.1 4.0bpw H6 EXL2195K / 18 GB181
Smaugv0.1 8.0bpw H8 EXL2195K / 34.9 GB151
Smaugv0.1 3.0bpw H6 EXL2195K / 13.9 GB141
Mistral 7B A U0.5 B2 Ver0.432K / 14.4 GB48730
Mistral 7B OP U1k Ver0.632K / 14.4 GB48730
Mistral 7B Openplatypus 1K32K / 29 GB12050
Mistral 7B OpenOrca 1K32K / 29 GB12013
Mistral 7B SlimOrca OP 8K32K / 14.4 GB25280
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/Smaugv0.1-4.65bpw-h6-exl2.

Rank the Smaugv0.1 4.65bpw 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? 40013 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 v20241217
  Support LLM Explorer