PULSE 20bv5 by OpenMEDLab

 ยป  All LLMs  ยป  OpenMEDLab  ยป  PULSE 20bv5   URL Share it on

  Autotrain compatible   Conversational   Endpoints compatible   Llama   Pulse   Pytorch   Region:us   Safetensors   Zh
Model Card on HF ๐Ÿค—: https://huggingface.co/OpenMEDLab/PULSE-20bv5 

PULSE 20bv5 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
PULSE 20bv5 (OpenMEDLab/PULSE-20bv5)

PULSE 20bv5 Parameters and Internals

Model Type 
Natural Language Processing, Medical NLP
Use Cases 
Areas:
Medical domain
Applications:
Health education, Physician examination, Report interpretation, Medical records restructuring, Simulated diagnosis and treatment
Primary Use Cases:
Medical question answering, Health consultation
Limitations:
The model cannot replace professional medical advice.
Considerations:
Users should seek professional medical help for diagnosis or treatment.
Supported Languages 
Chinese (Native)
Training Details 
Data Sources:
Medical domain, General domain
Data Volume:
4,000,000 examples
Methodology:
Fine-tuning
Input Output 
Accepted Modalities:
text
LLM NamePULSE 20bv5
Repository ๐Ÿค—https://huggingface.co/OpenMEDLab/PULSE-20bv5 
Model Size20.1b
Required VRAM0.6 GB
Updated2025-05-15
MaintainerOpenMEDLab
Model Typellama
Model Files  1.1 GB: 1-of-63   0.6 GB: 2-of-63   0.6 GB: 3-of-63   0.6 GB: 4-of-63   0.6 GB: 5-of-63   0.6 GB: 6-of-63   0.6 GB: 7-of-63   0.6 GB: 8-of-63   0.6 GB: 9-of-63   0.6 GB: 10-of-63   0.6 GB: 11-of-63   0.6 GB: 12-of-63   0.6 GB: 13-of-63   0.6 GB: 14-of-63   0.6 GB: 15-of-63   0.6 GB: 16-of-63   0.6 GB: 17-of-63   0.6 GB: 18-of-63   0.6 GB: 19-of-63   0.6 GB: 20-of-63   0.6 GB: 21-of-63   0.6 GB: 22-of-63   0.6 GB: 23-of-63   0.6 GB: 24-of-63   0.6 GB: 25-of-63   0.6 GB: 26-of-63   0.6 GB: 27-of-63   0.6 GB: 28-of-63   0.6 GB: 29-of-63   0.6 GB: 30-of-63   0.6 GB: 31-of-63   0.6 GB: 32-of-63   0.6 GB: 33-of-63   0.6 GB: 34-of-63   0.6 GB: 35-of-63   0.6 GB: 36-of-63   0.6 GB: 37-of-63   0.6 GB: 38-of-63   0.6 GB: 39-of-63   0.6 GB: 40-of-63   0.6 GB: 41-of-63   0.6 GB: 42-of-63   0.6 GB: 43-of-63   0.6 GB: 44-of-63   0.6 GB: 45-of-63   0.6 GB: 46-of-63
Supported Languageszh
Model ArchitectureLlamaForCausalLM
Licenseagpl-3.0
Context Length16384
Model Max Length16384
Transformers Version4.33.3
Vocabulary Size103424
Torch Data Typebfloat16

Rank the PULSE 20bv5 Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 47368 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227