Instructions to use nagham-mlb/supportbot-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nagham-mlb/supportbot-model with Transformers:

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

pipe = pipeline("text-generation", model="nagham-mlb/supportbot-model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nagham-mlb/supportbot-model")
model = AutoModelForCausalLM.from_pretrained("nagham-mlb/supportbot-model")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nagham-mlb/supportbot-model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nagham-mlb/supportbot-model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nagham-mlb/supportbot-model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nagham-mlb/supportbot-model

SGLang

How to use nagham-mlb/supportbot-model 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 "nagham-mlb/supportbot-model" \
    --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": "nagham-mlb/supportbot-model",
		"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 "nagham-mlb/supportbot-model" \
        --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": "nagham-mlb/supportbot-model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nagham-mlb/supportbot-model with Docker Model Runner:
```
docker model run hf.co/nagham-mlb/supportbot-model
```

supportbot-model / README.md

nagham-mlb

updated readme

a7690fc verified 3 months ago

preview code

Raw

History Blame Contribute Delete

1.65 kB

	---
	language: en
	library_name: transformers
	pipeline_tag: text-generation
	license: mit
	tags:
	- conversational
	- dialogue
	- customer-support
	- text-generation
	- distilgpt2
	base_model: distilgpt2
	inference:
	parameters:
	max_new_tokens: 100
	temperature: 0.7
	do_sample: true
	top_p: 0.9
	widget:
	- text: "User: How do I reset my password?\nBot:"
	example_title: "Password Reset"
	- text: "User: What are your business hours?\nBot:"
	example_title: "Business Hours"
	- text: "User: How do I track my order?\nBot:"
	example_title: "Order Tracking"
	- text: "User: How do I contact support?\nBot:"
	example_title: "Contact Support"
	- text: "User: What is your return policy?\nBot:"
	example_title: "Return Policy"
	---

	# SupportBot Customer Support Model

	This model is a fine-tuned version of `distilgpt2` specifically designed for customer support conversations on the SupportBot platform.

	## Model Description

	A conversational AI model that provides helpful, accurate responses to common customer support queries including password resets, order tracking, return policies, account management, and troubleshooting.

	## Intended Uses

	This model is designed to:
	- Answer customer support questions automatically
	- Provide consistent, accurate responses
	- Reduce human agent workload
	- Offer 24/7 support availability

	## How to Use

	### Python (Transformers)

	```python
	from transformers import pipeline

	generator = pipeline('text-generation', model='nagham-mlb/supportbot-model')

	prompt = "User: How do I reset my password?\nBot:"
	response = generator(prompt, max_new_tokens=100, temperature=0.7)
	print(response[0]['generated_text'])