Instructions to use MEDT/ChatBot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MEDT/ChatBot with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MEDT/ChatBot") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("MEDT/ChatBot") model = AutoModelForCausalLM.from_pretrained("MEDT/ChatBot") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use MEDT/ChatBot with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MEDT/ChatBot" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MEDT/ChatBot", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/MEDT/ChatBot
- SGLang
How to use MEDT/ChatBot 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 "MEDT/ChatBot" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MEDT/ChatBot", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "MEDT/ChatBot" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MEDT/ChatBot", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use MEDT/ChatBot with Docker Model Runner:
docker model run hf.co/MEDT/ChatBot
Update README.md
Browse files
README.md
CHANGED
|
@@ -25,8 +25,8 @@ tokenizer = AutoTokenizer.from_pretrained("r3dhummingbird/DialoGPT-medium-joshua
|
|
| 25 |
|
| 26 |
model = AutoModelWithLMHead.from_pretrained("r3dhummingbird/DialoGPT-medium-joshua")
|
| 27 |
|
| 28 |
-
# Let's chat for
|
| 29 |
-
for step in range(
|
| 30 |
# encode the new user input, add the eos_token and return a tensor in Pytorch
|
| 31 |
new_user_input_ids = tokenizer.encode(input(">> User:") + tokenizer.eos_token, return_tensors='pt')
|
| 32 |
# print(new_user_input_ids)
|
|
|
|
| 25 |
|
| 26 |
model = AutoModelWithLMHead.from_pretrained("r3dhummingbird/DialoGPT-medium-joshua")
|
| 27 |
|
| 28 |
+
# Let's chat for 100 lines
|
| 29 |
+
for step in range(100):
|
| 30 |
# encode the new user input, add the eos_token and return a tensor in Pytorch
|
| 31 |
new_user_input_ids = tokenizer.encode(input(">> User:") + tokenizer.eos_token, return_tensors='pt')
|
| 32 |
# print(new_user_input_ids)
|