Instructions to use jana-ashraf-ai/python-assistant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jana-ashraf-ai/python-assistant with Transformers:

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

pipe = pipeline("text-generation", model="jana-ashraf-ai/python-assistant")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jana-ashraf-ai/python-assistant")
model = AutoModelForCausalLM.from_pretrained("jana-ashraf-ai/python-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]:]))

Inference
Local Apps Settings

vLLM

How to use jana-ashraf-ai/python-assistant with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jana-ashraf-ai/python-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": "jana-ashraf-ai/python-assistant",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jana-ashraf-ai/python-assistant

SGLang

How to use jana-ashraf-ai/python-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 "jana-ashraf-ai/python-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": "jana-ashraf-ai/python-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 "jana-ashraf-ai/python-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": "jana-ashraf-ai/python-assistant",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jana-ashraf-ai/python-assistant with Docker Model Runner:
```
docker model run hf.co/jana-ashraf-ai/python-assistant
```

jana-ashraf-ai commited on Apr 2

Commit

d8d9cba

verified ·

1 Parent(s): 288967a

Update README.md

Browse files

Files changed (1) hide show

README.md +8 -8

README.md CHANGED Viewed

@@ -1,4 +1,4 @@
 library_name: transformers
 license: apache-2.0
 base_model: Qwen/Qwen2.5-1.5B-Instruct
@@ -17,13 +17,13 @@ tags:
 - code
 - instruction-tuning
 - fine-tuned
 # 🐍 Python Assistant (Arabic)
 A fine-tuned version of **Qwen2.5-1.5B-Instruct** that answers Python programming questions in **Arabic**, with structured JSON output. Fine-tuned using LoRA via LLaMA-Factory.
 ## Model Details
@@ -34,13 +34,13 @@ A fine-tuned version of **Qwen2.5-1.5B-Instruct** that answers Python programmin
 - **License:** Apache 2.0
 - **Fine-tuning method:** QLoRA (LoRA rank=32) via LLaMA-Factory
 ## What does this model do?
 Given a Python programming question in English, the model returns a structured JSON answer **in Arabic**, explaining the solution step by step.
 ## How to Use
 ```python
@@ -74,7 +74,7 @@ outputs = model.generate(**inputs, max_new_tokens=512)
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```
 ## Training Details
@@ -95,7 +95,7 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 | Framework | LLaMA-Factory |
 | Hardware | Google Colab T4 GPU |
 ## Training Data
@@ -105,7 +105,7 @@ The answers were annotated and structured using GPT to produce Arabic explanatio
 **Train / Val split:** 90% / 10%
 ## Limitations

+---
 library_name: transformers
 license: apache-2.0
 base_model: Qwen/Qwen2.5-1.5B-Instruct
 - code
 - instruction-tuning
 - fine-tuned
+---
 # 🐍 Python Assistant (Arabic)
 A fine-tuned version of **Qwen2.5-1.5B-Instruct** that answers Python programming questions in **Arabic**, with structured JSON output. Fine-tuned using LoRA via LLaMA-Factory.
+---
 ## Model Details
 - **License:** Apache 2.0
 - **Fine-tuning method:** QLoRA (LoRA rank=32) via LLaMA-Factory
+---
 ## What does this model do?
 Given a Python programming question in English, the model returns a structured JSON answer **in Arabic**, explaining the solution step by step.
+---
 ## How to Use
 ```python
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```
+---
 ## Training Details
 | Framework | LLaMA-Factory |
 | Hardware | Google Colab T4 GPU |
+---
 ## Training Data
 **Train / Val split:** 90% / 10%
+---
 ## Limitations