Instructions to use RobCzikkel/DoctorGPT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RobCzikkel/DoctorGPT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="RobCzikkel/DoctorGPT")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("RobCzikkel/DoctorGPT") model = AutoModelForCausalLM.from_pretrained("RobCzikkel/DoctorGPT") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use RobCzikkel/DoctorGPT with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "RobCzikkel/DoctorGPT" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "RobCzikkel/DoctorGPT", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/RobCzikkel/DoctorGPT
- SGLang
How to use RobCzikkel/DoctorGPT with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "RobCzikkel/DoctorGPT" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "RobCzikkel/DoctorGPT", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "RobCzikkel/DoctorGPT" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "RobCzikkel/DoctorGPT", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use RobCzikkel/DoctorGPT with Docker Model Runner:
docker model run hf.co/RobCzikkel/DoctorGPT
Commit ·
1114470
1
Parent(s): 77eb049
Update README.md
Browse files
README.md
CHANGED
|
@@ -22,13 +22,14 @@ It achieves the following results on the evaluation set:
|
|
| 22 |
The base model used is Microsoft's BioGPT, it was fine-tuned with a custom prompt for a conversational chatbot between a patient and a doctor.
|
| 23 |
The prompt used is as follows:
|
| 24 |
|
| 25 |
-
|
| 26 |
-
You are a Doctor. Below is a question from a patient. Write a response to the patient that answers their question\n\n"
|
| 27 |
|
| 28 |
### Patient: {question}"
|
| 29 |
|
| 30 |
### Doctor: {answer}
|
| 31 |
"""
|
|
|
|
| 32 |
|
| 33 |
## Intended uses & limitations
|
| 34 |
|
|
|
|
| 22 |
The base model used is Microsoft's BioGPT, it was fine-tuned with a custom prompt for a conversational chatbot between a patient and a doctor.
|
| 23 |
The prompt used is as follows:
|
| 24 |
|
| 25 |
+
```py
|
| 26 |
+
"""You are a Doctor. Below is a question from a patient. Write a response to the patient that answers their question\n\n"
|
| 27 |
|
| 28 |
### Patient: {question}"
|
| 29 |
|
| 30 |
### Doctor: {answer}
|
| 31 |
"""
|
| 32 |
+
```
|
| 33 |
|
| 34 |
## Intended uses & limitations
|
| 35 |
|