Instructions to use abdelfetteh/tunisian-chatbot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abdelfetteh/tunisian-chatbot with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("abdelfetteh/tunisian-chatbot")
model = AutoModelForCausalLM.from_pretrained("abdelfetteh/tunisian-chatbot")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use abdelfetteh/tunisian-chatbot with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/abdelfetteh/tunisian-chatbot

SGLang

How to use abdelfetteh/tunisian-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 "abdelfetteh/tunisian-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": "abdelfetteh/tunisian-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 "abdelfetteh/tunisian-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": "abdelfetteh/tunisian-chatbot",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use abdelfetteh/tunisian-chatbot with Docker Model Runner:
```
docker model run hf.co/abdelfetteh/tunisian-chatbot
```

Tunisian Chatbot 🇹🇳

A fine-tuned conversational model specifically optimized for Tunisian Derja (Arabic dialect) to provide natural and helpful customer support interactions.

Model Overview

Understanding and responding in Tunisian Derja
Providing product recommendations
Handling customer service inquiries
Maintaining natural, friendly conversations
Developed by: Abdelfetteh
Language: Tunisian Derja (aeb), Arabic (ar), French (fr)
License: apache-2.0

Model Details

Model Type: Causal Language Model (7B parameters)
Format: 16-bit (float16)
Context Length: 4096 tokens
Training Data: Customer service conversations, product catalogs, and support interactions

Quick Start

Installation

pip install transformers torch accelerate

Downloads last month: 41

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for abdelfetteh/tunisian-chatbot

Unable to build the model tree, the base model loops to the model itself. Learn more.