Instructions to use saifamdouni/TunChat-V0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use saifamdouni/TunChat-V0.1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="saifamdouni/TunChat-V0.1") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("saifamdouni/TunChat-V0.1") model = AutoModelForMultimodalLM.from_pretrained("saifamdouni/TunChat-V0.1") 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 Settings
- vLLM
How to use saifamdouni/TunChat-V0.1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "saifamdouni/TunChat-V0.1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "saifamdouni/TunChat-V0.1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/saifamdouni/TunChat-V0.1
- SGLang
How to use saifamdouni/TunChat-V0.1 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 "saifamdouni/TunChat-V0.1" \ --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": "saifamdouni/TunChat-V0.1", "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 "saifamdouni/TunChat-V0.1" \ --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": "saifamdouni/TunChat-V0.1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use saifamdouni/TunChat-V0.1 with Docker Model Runner:
docker model run hf.co/saifamdouni/TunChat-V0.1
# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM
tokenizer = AutoTokenizer.from_pretrained("saifamdouni/TunChat-V0.1")
model = AutoModelForMultimodalLM.from_pretrained("saifamdouni/TunChat-V0.1")
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]:]))Model Card: TunChat-V0.1
Model Overview:
- Model Name: TunChat-V0.1
- Model Size: 2B parameters
- Instruction-Tuned: Yes
- Language: Tunisian Dialect
- Use Case Focus: Conversational exchanges, translation, summarization, content generation, and cultural research.
Model Description: TunChat-V0.1 is a 2-billion parameter language model specifically instruction-tuned for the Tunisian dialect. It is designed to handle tasks such as conversational exchanges, informal text summarization, and culturally-aware content generation. The model is optimized to understand and generate text in Tunisian Dialect, enabling enhanced performance for applications targeting Tunisian users.
Intended Use:
- Conversational agents and chatbots operating in Tunisian Dialect.
- Translation, summarization, and content generation in informal Tunisian dialect.
- Supporting cultural research related to Tunisian language and heritage.
How to Use:
import torch
from transformers import pipeline
pipe = pipeline(
"text-generation",
model="saifamdouni/TunChat-V0.1",
model_kwargs={"torch_dtype": torch.bfloat16},
device="cuda" # replace with "mps" to run on a Mac device
)
messages = [
{"role": "user", "content": 'احكيلي على تونس'},
]
outputs = pipe(messages,
max_new_tokens=2048,
do_sample=True,
top_p=0.95,
temperature=0.7,
top_k=50)
assistant_response = outputs[0]["generated_text"][-1]["content"].strip()
print(assistant_response)
تونس بلاد موجودة في شمال افريقيا، في الجنوب متاع البحر الأبيض المتوسط. عندها حدود مع ليبيا و الجزائر. تونس عندها مساحة جملية تقريب 176،700 كيلومتر مربع، و عدد سكان يوصل ل 11.7 مليون نسمة. العاصمة متاعها و أكبر مدينة هي تونس العاصمة، و العاصمة السياسية و الاقتصادية. تونس عندها تاريخ غني و ثقافة متنوعة، و فيها برشا معالم أثرية، كيما قرطاج، اللي كانت مدينة قديمة و مركز تجاري مهم في قرطاج القديمة. تونس عندها نظام اقتصادي متنوع، و قطاع الخدمات هو أكبر قطاع في البلاد. زيد على هذا، قطاع السياحة مهم زادة، خاطر البلاد معروفة بالبلايص التاريخية متاعها، الماكلة و الثقافة. في الخلاصة، تونس بلاد متنوعة و فيها برشا حاجات، عندها تاريخ غني، ثقافة فريدة و مناظر طبيعية خلابة.
Quantized Versions:
- GGUF quantized versions will be released later.
Training Dataset:
- Tun-SFT dataset (to be released later):
- A mix between organically collected and synthetically generated data
Limitations and Ethical Considerations:
- The model may occasionally produce incorrect or biased responses.
- The model may occasionally produce culturally inappropriate responses.
- It may not perform optimally on formal Tunisian Arabic texts.
Future Plans:
- Release of GGUF quantized versions.
- Open-source availability of the Tun-SFT dataset.
Author: Saif Eddine Amdouni
- Downloads last month
- 13
Model tree for saifamdouni/TunChat-V0.1
Base model
unsloth/gemma-2-2b-it
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="saifamdouni/TunChat-V0.1") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)