Downloads · 30 days
18
4% of all-time downloads
galen
ahmed-ai/galen
galen is a text generation model from ahmed-ai. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
Galen is fine-tuned from Mistral-7B-Instruct-v0.2, using medical quesion answering dataset Install "accelerate" to use CUDA GPU
All-time downloads
427
Public
Parameters
7.5B
8.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.1 GB · 100%
Parameter types
How the weights are stored.
U87.2B · 96%
Try a prompt
Datasets
Model card
From the Hugging Face model README
Galen
Galen is fine-tuned from Mistral-7B-Instruct-v0.2, using medical quesion answering dataset
Galen's view about future of medicine and AI:
Get Started
Install "accelerate" to use CUDA GPU
pip install accelerate
from transformers import AutoTokenizer, pipeline
tokenizer = AutoTokenizer.from_pretrained('ahmed-ai/galen')
model_pipeline = pipeline(task="text-generation", model='ahmed-ai/galen', tokenizer=tokenizer, max_length=256, temperature=0.5, top_p=0.6)
result = model_pipeline('What is squamous cell carcinoma')
#print the generated text
print(result[0]['generated_text'][len(prompt):])
- Task
- Text Generation
- Library
- transformers
- Type
- mistral
- License
- mit
- Languages
- en
- Created
- Jan 3, 2024
- Updated
- Dec 9, 2024