AquilaMed RL by BAAI

 ยป  All LLMs  ยป  BAAI  ยป  AquilaMed RL   URL Share it on

  Arxiv:2406.12182   Aquila3   Autotrain compatible   Conversational   Custom code Dataset:baai/aquilamed-instruc...   Dataset:baai/aquilamed-rl   Endpoints compatible   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/BAAI/AquilaMed-RL 

AquilaMed RL Benchmarks

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

AquilaMed RL Parameters and Internals

Model Type 
Large Language Model
Use Cases 
Areas:
Medical field
Primary Use Cases:
Medical triage, Medication inquiries, General Q&A
Additional Notes 
Building upon the Aquila model with continued pre-training, SFT, and RL; professional capabilities in the medical field
Training Details 
Data Sources:
BAAI/AquilaMed-Instruct, BAAI/AquilaMed-RL
Methodology:
Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL)
LLM NameAquilaMed RL
Repository ๐Ÿค—https://huggingface.co/BAAI/AquilaMed-RL 
Model Size8.2b
Required VRAM16.4 GB
Updated2025-02-22
MaintainerBAAI
Model Typeaquila3
Model Files  4.9 GB: 1-of-4   4.9 GB: 2-of-4   5.0 GB: 3-of-4   1.6 GB: 4-of-4   0.0 GB
Model ArchitectureAquilaForCausalLM
Licenseother
Context Length4096
Model Max Length4096
Transformers Version4.38.2
Tokenizer ClassQWenTokenizer
Padding Token<|endoftext|>
Vocabulary Size151851
Torch Data Typebfloat16

Rank the AquilaMed RL 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? 43470 in total.

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