Instructions to use abdallah3id/ABD3ID-CodeMentor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abdallah3id/ABD3ID-CodeMentor with Transformers:

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

pipe = pipeline("text-generation", model="abdallah3id/ABD3ID-CodeMentor")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("abdallah3id/ABD3ID-CodeMentor")
model = AutoModelForMultimodalLM.from_pretrained("abdallah3id/ABD3ID-CodeMentor", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use abdallah3id/ABD3ID-CodeMentor with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "abdallah3id/ABD3ID-CodeMentor"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "abdallah3id/ABD3ID-CodeMentor",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/abdallah3id/ABD3ID-CodeMentor

SGLang

How to use abdallah3id/ABD3ID-CodeMentor 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 "abdallah3id/ABD3ID-CodeMentor" \
    --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": "abdallah3id/ABD3ID-CodeMentor",
		"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 "abdallah3id/ABD3ID-CodeMentor" \
        --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": "abdallah3id/ABD3ID-CodeMentor",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use abdallah3id/ABD3ID-CodeMentor with Docker Model Runner:
```
docker model run hf.co/abdallah3id/ABD3ID-CodeMentor
```

abdallah3id commited on 23 days ago

Commit

9515fee

verified ·

1 Parent(s): 8d5052d

Create README.md

Browse files

Files changed (1) hide show

README.md +36 -0

README.md ADDED Viewed

	@@ -0,0 +1,36 @@

+---
+tags:
+  - lora
+  - code
+  - education
+  - vscode
+  - research
+  - work-in-progress
+---
+# ABD3ID CodeMentor
+**A planned LoRA research project for developer education and coding assistance in Visual Studio Code, maintained by Abdallah Eid.**
+## Project overview
+CodeMentor explores adaptation of a coding language model for clear explanations, guided debugging, and practical software engineering education. The intended experience emphasizes understanding the reasoning behind code changes and helping learners build independent problem-solving skills.
+## Development status
+This repository currently contains project documentation only. Model weights and LoRA adapters have not yet been uploaded. The base model, parameter scale, training data, and evaluation methodology remain to be finalized. No trained capabilities, benchmark scores, or working VS Code integration are claimed at this stage.
+## Intended research scope
+- Explain code, APIs, error messages, and implementation tradeoffs.
+- Guide debugging through hypotheses and verification steps.
+- Suggest refactoring, tests, and maintainable coding practices.
+- Support programming exercises and contextual learning within VS Code.
+## Planned integration
+After training and evaluation, the project aims to support an editor assistant through a documented inference endpoint or local serving workflow. A VS Code extension or compatible client must be configured separately; this repository is not itself an installed extension.
+## Release documentation
+A future release should include adapter weights and configuration, the exact base-model revision, training and dataset documentation, reproducible coding evaluations, inference examples, and editor integration instructions.
+## Limitations
+Generated code may contain functional, security, or compatibility errors. Review proposed changes and run appropriate tests before use. Do not expose secrets or private source code to an unapproved inference service.
+All right reserved | Designed by [Abdallah Eid](https://api.whatsapp.com/send/?phone=971551806906)