Instructions to use MBZUAI-Paris/Nile-Chat-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MBZUAI-Paris/Nile-Chat-4B with Transformers:

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

pipe = pipeline("text-generation", model="MBZUAI-Paris/Nile-Chat-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MBZUAI-Paris/Nile-Chat-4B")
model = AutoModelForCausalLM.from_pretrained("MBZUAI-Paris/Nile-Chat-4B")
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 MBZUAI-Paris/Nile-Chat-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MBZUAI-Paris/Nile-Chat-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MBZUAI-Paris/Nile-Chat-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MBZUAI-Paris/Nile-Chat-4B

SGLang

How to use MBZUAI-Paris/Nile-Chat-4B 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 "MBZUAI-Paris/Nile-Chat-4B" \
    --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": "MBZUAI-Paris/Nile-Chat-4B",
		"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 "MBZUAI-Paris/Nile-Chat-4B" \
        --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": "MBZUAI-Paris/Nile-Chat-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MBZUAI-Paris/Nile-Chat-4B with Docker Model Runner:
```
docker model run hf.co/MBZUAI-Paris/Nile-Chat-4B
```

amr-mohamed commited on Jun 3, 2025

Commit

88d290c

verified ·

1 Parent(s): 663ae82

Added overall scores plot

Browse files

Files changed (3) hide show

.gitattributes +1 -0
README.md +1 -1
overall_benchmark_scores.png +3 -0

.gitattributes CHANGED Viewed

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text

 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overall_benchmark_scores.png filter=lfs diff=lfs merge=lfs -text

README.md CHANGED Viewed

@@ -17,7 +17,7 @@ base_model:
 # JAIS Initiative: Nile-Chat Models
 ## Model Overview
 Nile-Chat is a family of open instruction-tuned models for Egyptian dialect, developed to handle both scripts commonly used in Egypt: Arabic script and Latin-based Arabizi. As part of the [Jais](https://arxiv.org/abs/2308.16149) project for standard Arabic and its extensions to dialectal Arabic, Nile-Chat is designed to support natural language generation in a way that reflects the script-diverse nature of Egyptian communication. These models are effective for a variety of tasks including question answering, translation and transliteration. Their range of sizes ensures accessibility, from lightweight personal deployments to more powerful setups, enabling broader use of AI technologies for Egyptian Arabic speakers. The family includes two versions:
 * [Nile-Chat-4B](https://huggingface.co/MBZUAI-Paris/Nile-Chat-4B): A compact 4B parameter model that balances efficiency and fluency, well-suited for generating Egyptian Arabic in both Arabic and Latin scripts.

 # JAIS Initiative: Nile-Chat Models
 ## Model Overview
+![overall benchmark scores](overall_benchmark_scores.png)
 Nile-Chat is a family of open instruction-tuned models for Egyptian dialect, developed to handle both scripts commonly used in Egypt: Arabic script and Latin-based Arabizi. As part of the [Jais](https://arxiv.org/abs/2308.16149) project for standard Arabic and its extensions to dialectal Arabic, Nile-Chat is designed to support natural language generation in a way that reflects the script-diverse nature of Egyptian communication. These models are effective for a variety of tasks including question answering, translation and transliteration. Their range of sizes ensures accessibility, from lightweight personal deployments to more powerful setups, enabling broader use of AI technologies for Egyptian Arabic speakers. The family includes two versions:
 * [Nile-Chat-4B](https://huggingface.co/MBZUAI-Paris/Nile-Chat-4B): A compact 4B parameter model that balances efficiency and fluency, well-suited for generating Egyptian Arabic in both Arabic and Latin scripts.

overall_benchmark_scores.png ADDED Viewed

Git LFS Details

SHA256: 37c64ce1e1afba9d7a71e97d1cd386028c4111d0600b15c501c0537d2ca518d4
Pointer size: 132 Bytes
Size of remote file: 1.7 MB