Instructions to use MEDT/Chatbot_Medium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MEDT/Chatbot_Medium with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="MEDT/Chatbot_Medium")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MEDT/Chatbot_Medium")
model = AutoModelForCausalLM.from_pretrained("MEDT/Chatbot_Medium", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MEDT/Chatbot_Medium with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MEDT/Chatbot_Medium"
# 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_Medium",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MEDT/Chatbot_Medium

SGLang

How to use MEDT/Chatbot_Medium 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_Medium" \
    --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_Medium",
		"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_Medium" \
        --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_Medium",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MEDT/Chatbot_Medium with Docker Model Runner:
```
docker model run hf.co/MEDT/Chatbot_Medium
```

Chatbot_Medium

Commit History

Jun 1, 2023

14:48
Adding `safetensors` variant of this model⁠

SFconvertbot

96b3ea6

Apr 24, 2022

15:30
Upload vocab.json

MEDT

782a9bd
15:30
Upload tokenizer_config.json

MEDT

a12cce5
15:28
Upload tf_model.h5 with git-lfs

MEDT

d28ed29
15:25
Upload rust_model.ot with git-lfs

MEDT

f3c1b98
15:21
Upload README.md

MEDT

d8ff54f
15:21
Upload pytorch_model.bin with git-lfs

MEDT

dc0f981
15:19
Upload merges.txt

MEDT

97a3549
15:19
Upload config.json

MEDT

f77d858
15:16
Upload flax_model.msgpack with git-lfs

MEDT

759e1fe
15:13
initial commit

MEDT

5781c29

Commit History

Jun 1, 2023

Adding `safetensors` variant of this model⁠

Apr 24, 2022

Upload vocab.json

Upload tokenizer_config.json

Upload tf_model.h5 with git-lfs

Upload rust_model.ot with git-lfs

Upload README.md

Upload pytorch_model.bin with git-lfs

Upload merges.txt

Upload config.json

Upload flax_model.msgpack with git-lfs

initial commit