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

Sirius 10B by FelixChao

 »  All LLMs  »  FelixChao  »  Sirius 10B   URL Share it on

  1103   
  Merged Model   Autotrain compatible   Endpoints compatible   Felixchao/severus-7b   Leveldevai/turdusbeagle-7b   Mistral   Region:us   Safetensors   Sharded   Tensorflow

Sirius 10B Benchmarks

ARC: 71.93 vs 96.7 (so35)-25.6%
HellaSwag: 87.32 vs 95.3 (gpt4)-8.4%
MMLU: 64.73 vs 88.3 (so35)-26.7%
TruthfulQA: 68.1 vs 59 (gpt4)15.4%
WinoGrande: 82.79 vs 87.5 (gpt4)-5.4%
GSM8K: 62.09 vs 96.4 (so35)-35.6%
LLME Score: 0.2051
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Sirius 10B Parameters and Internals

LLM NameSirius 10B
Repository 🤗https://huggingface.co/FelixChao/Sirius-10B 
Merged ModelYes
Model Size10b
Required VRAM21.5 GB
Updated2024-10-22
MaintainerFelixChao
Model Typemistral
Model Files  10.0 GB: 1-of-3   10.0 GB: 2-of-3   1.5 GB: 3-of-3
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16
Sirius 10B (FelixChao/Sirius-10B)

Best Alternatives to Sirius 10B

Best Alternatives
Context / RAM
Downloads
Likes
Contrail 200M 64K64K / 0.4 GB92
Contrail 200M 64K64K / 0.4 GB00
NarutoDolphin 10B32K / 21.5 GB11162
Mistral Passthrough 8L 10B32K / 14.5 GB11410
Occiglot10b DPO32K / 19.7 GB41
...penbuddy Mistral 10B V17.1 32K32K / 21.5 GB25
Voldemort 10B8K / 21.5 GB11170
Voldemort 10B DPO8K / 21.4 GB5850
...l 10B V17.1 32K 8.0bpw H8 EXL232K / 10.9 GB51
Note: green Score (e.g. "73.2") means that the model is better than FelixChao/Sirius-10B.

Rank the Sirius 10B 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? 37106 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 v2024072803
  Support LLM Explorer