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

Medusa 1.1 L2 7B by Sao10K

 »  All LLMs  »  Sao10K  »  Medusa 1.1 L2 7B   URL Share it on

  0   
  Autotrain compatible   En   Endpoints compatible   License:llama2   Llama   Region:us   Safetensors   Sharded   Tensorflow

Medusa 1.1 L2 7B Benchmarks

ARC: 56.48 vs 96.7 (so35)-41.6%
HellaSwag: 78.57 vs 95.3 (gpt4)-17.6%
MMLU: 51.56 vs 88.3 (so35)-41.6%
TruthfulQA: 47.7 vs 59 (gpt4)-19.2%
WinoGrande: 75.06 vs 87.5 (gpt4)-14.2%
GSM8K: 1.44 vs 96.4 (so35)-98.5%
LLME Score: 0.27768
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Medusa 1.1 L2 7B Parameters and Internals

LLM NameMedusa 1.1 L2 7B
Repository 🤗https://huggingface.co/Sao10K/Medusa-1.1-L2-7B 
Model Size7b
Required VRAM14 GB
Updated2024-07-04
MaintainerSao10K
Model Typellama
Model Files  10.2 GB: 1-of-2   3.8 GB: 2-of-2
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.32.1
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16
Medusa 1.1 L2 7B (Sao10K/Medusa-1.1-L2-7B)

Best Alternatives to Medusa 1.1 L2 7B

Best Alternatives
Context / RAM
Downloads
Likes
...1M 1000000ctx AEZAKMI 3 1 17021024K / 13.5 GB571
... Qwen2.5llamaify 7B V23.1 200K195K / 15.2 GB6840
Yarn Llama 2 7B 128K128K / 13.5 GB160938
LLaMA 7B PoSE YaRN 128K128K / 13.5 GB13
LLaMA 7B PoSE Linear 96K96K / 27 GB62
LLaMA 7B PoSE YaRN 96K96K / 13.5 GB11
Chat Llama2 7B 80K80K / 13.8 GB120
Llama2 7B 80K80K / 13.8 GB60
Lloma Step40064K / 13.5 GB570
Lloma Step20064K / 13.5 GB600
Note: green Score (e.g. "73.2") means that the model is better than Sao10K/Medusa-1.1-L2-7B.

Rank the Medusa 1.1 L2 7B 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? 36966 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