Instructions to use youssefbelghmi/MNLP_M3_mcqa_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use youssefbelghmi/MNLP_M3_mcqa_model with Transformers:

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

pipe = pipeline("text-generation", model="youssefbelghmi/MNLP_M3_mcqa_model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("youssefbelghmi/MNLP_M3_mcqa_model")
model = AutoModelForCausalLM.from_pretrained("youssefbelghmi/MNLP_M3_mcqa_model")
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 youssefbelghmi/MNLP_M3_mcqa_model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "youssefbelghmi/MNLP_M3_mcqa_model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "youssefbelghmi/MNLP_M3_mcqa_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/youssefbelghmi/MNLP_M3_mcqa_model

SGLang

How to use youssefbelghmi/MNLP_M3_mcqa_model 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 "youssefbelghmi/MNLP_M3_mcqa_model" \
    --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": "youssefbelghmi/MNLP_M3_mcqa_model",
		"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 "youssefbelghmi/MNLP_M3_mcqa_model" \
        --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": "youssefbelghmi/MNLP_M3_mcqa_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use youssefbelghmi/MNLP_M3_mcqa_model with Docker Model Runner:
```
docker model run hf.co/youssefbelghmi/MNLP_M3_mcqa_model
```

youssefbelghmi commited on Jun 9, 2025

Commit

254a84b

verified ·

1 Parent(s): 4eb2fec

Update README.md

Browse files

Files changed (1) hide show

README.md +15 -15

README.md CHANGED Viewed

@@ -12,9 +12,9 @@ licence: license
 # MNLP M3 MCQA Model (Qwen3-0.6B fine-tuned)
-This model is a fine-tuned version of [tocico28/MNLP_M3_dpo_model](https://huggingface.co/tocico28/MNLP_M3_dpo_model) on the [youssefbelghmi/MNLP_M3_mcqa_dataset](https://huggingface.co/datasets/youssefbelghmi/MNLP_M3_mcqa_dataset) dataset, a large-scale collection of multiple-choice questions designed for evaluating and training models in **STEM** domains (science, math, engineering, medicine, etc.).
-The [tocico28/MNLP_M3_dpo_model](https://huggingface.co/tocico28/MNLP_M3_dpo_model) model is itself a fine-tuned version of **Qwen/Qwen3-0.6B-Base** using a dataset of preference-labeled STEM response pairs collected through a collaborative classroom annotation effort.
 It has been trained using [TRL](https://github.com/huggingface/trl) as part of the final milestone of the **CS-552: Modern NLP** course at EPFL (Spring 2025).
@@ -72,19 +72,19 @@ The following hyperparameters were used during training:
 ## Training Results
 |   Epoch |   Training Loss |   Validation Loss |
 |--------:|----------------:|------------------:|
-|    0.08 |          0.3461 |            0.2748 |
-|    0.15 |          0.2881 |            0.2666 |
-|    0.23 |          0.2938 |            0.2661 |
-|    0.31 |          0.2741 |            0.26   |
-|    0.38 |          0.2684 |            0.257  |
-|    0.46 |          0.2603 |            0.2539 |
-|    0.54 |          0.2635 |            0.2441 |
-|    0.61 |          0.2555 |            0.2457 |
-|    0.69 |          0.2459 |            0.2414 |
-|    0.77 |          0.2383 |            0.2353 |
-|    0.84 |          0.2266 |            0.2337 |
-|    0.92 |          0.2112 |            0.2338 |
-|    0.99 |          0.211  |            0.2335 |
 - **Final training loss:** 0.211
 - **Final validation accuracy:** ~92.0%
 ### Framework versions

 # MNLP M3 MCQA Model (Qwen3-0.6B fine-tuned)
+This model is a fine-tuned version of [tocico28/MNLP_M3_dpo_model](https://huggingface.co/tocico28/MNLP_M3_dpo_model) on the [youssefbelghmi/MNLP_M3_mcqa_dataset](https://huggingface.co/datasets/youssefbelghmi/MNLP_M3_mcqa_dataset), a large-scale collection of multiple-choice questions designed for evaluating and training models in **STEM** domains (science, math, engineering, medicine, etc.).
+The [tocico28/MNLP_M3_dpo_model](https://huggingface.co/tocico28/MNLP_M3_dpo_model) is itself a fine-tuned version of **Qwen/Qwen3-0.6B-Base** using a dataset of preference-labeled STEM response pairs collected through a collaborative classroom annotation effort.
 It has been trained using [TRL](https://github.com/huggingface/trl) as part of the final milestone of the **CS-552: Modern NLP** course at EPFL (Spring 2025).
 ## Training Results
 |   Epoch |   Training Loss |   Validation Loss |
 |--------:|----------------:|------------------:|
+|    0.08 |          0.3363 |            0.2766 |
+|    0.15 |          0.2938 |            0.2719 |
+|    0.23 |          0.2431 |            0.2604 |
+|    0.31 |          0.2688 |            0.2751 |
+|    0.38 |          0.2817 |            0.2571 |
+|    0.46 |          0.2106 |            0.2640 |
+|    0.54 |          0.2692 |            0.2439 |
+|    0.61 |          0.2321 |            0.2384 |
+|    0.69 |          0.2091 |            0.2340 |
+|    0.77 |          0.2495 |            0.2433 |
+|    0.84 |          0.2489 |            0.2376 |
+|    0.92 |          0.2363 |            0.2358 |
+|    0.99 |          0.2611 |            0.2353 |
 - **Final training loss:** 0.211
 - **Final validation accuracy:** ~92.0%
 ### Framework versions