Instructions to use abulbudz/mistral-palestinian-assistant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abulbudz/mistral-palestinian-assistant with Transformers:

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

pipe = pipeline("text-generation", model="abulbudz/mistral-palestinian-assistant")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("abulbudz/mistral-palestinian-assistant")
model = AutoModelForCausalLM.from_pretrained("abulbudz/mistral-palestinian-assistant")
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 abulbudz/mistral-palestinian-assistant with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/abulbudz/mistral-palestinian-assistant

SGLang

How to use abulbudz/mistral-palestinian-assistant 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 "abulbudz/mistral-palestinian-assistant" \
    --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": "abulbudz/mistral-palestinian-assistant",
		"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 "abulbudz/mistral-palestinian-assistant" \
        --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": "abulbudz/mistral-palestinian-assistant",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use abulbudz/mistral-palestinian-assistant with Docker Model Runner:
```
docker model run hf.co/abulbudz/mistral-palestinian-assistant
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Description

This model is a fine-tuned variant of mistralai/Mistral-7B-Instruct-v0.3, trained on PalGeo a specialized dataset that focuses on Palestine’s geography.

Developed by: Ahmad Budairi, Belal Hamdeh, Mitri Khoury
Language(s) (NLP): Arabic
Finetuned from model: mistralai/Mistral-7B-Instruct-v0.3

Contact

If you have any feedback, questions, comments, or constructive criticism about this model. please feel free to reach out via the community tab or by email:

✉️ Email: ahmadbudairi333@gmail.com

Training Hyperparameters

Parameter	Value
Lora_r	32
Lora_dropout	0.1
Bnb_4bit_quant_type	“nf4”
num_train_epoch	3
per_device_train_batch_size	4
per_device_eval_batch_size	4
gradient_checkpointing	True
learning_rate	4e-4
optim	“paged_adamw_8bit”
lora_alpha	64
bnb_4bit_compute_dtype	“bfloat16”
bf16	True
gradient_accumulation_steps	64
weight_decay	0.001

Technical Specifications

Hardware

A single NVIDIA GeForce RTX 4070

Downloads last month: 2

Safetensors

Model size

7B params

Tensor type

F16

Model tree for abulbudz/mistral-palestinian-assistant

Base model

mistralai/Mistral-7B-v0.3

Finetuned

mistralai/Mistral-7B-Instruct-v0.3

Finetuned

(494)

this model

Quantizations

1 model