Instructions to use medodeyaa/mistral-exam-generator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use medodeyaa/mistral-exam-generator with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("medodeyaa/mistral-exam-generator")
model = AutoModelForCausalLM.from_pretrained("medodeyaa/mistral-exam-generator", device_map="auto")
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 Settings

vLLM

How to use medodeyaa/mistral-exam-generator with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/medodeyaa/mistral-exam-generator

SGLang

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

Docker Model Runner
How to use medodeyaa/mistral-exam-generator with Docker Model Runner:
```
docker model run hf.co/medodeyaa/mistral-exam-generator
```

medodeyaa commited on Jun 15

Commit

23fbd7b

verified ·

1 Parent(s): 5f350e2

Update README.md

Browse files

Files changed (1) hide show

README.md +11 -6

README.md CHANGED Viewed

@@ -1,16 +1,21 @@
 ---
-license: apache-2.0
 language:
-- ar
-- en
 base_model: mistralai/Mistral-7B-v0.1
 pipeline_tag: text-generation
 tags:
-- quiz-generator
-- exam-generator
-- educational
 ---
 # Mistral Exam Generator (كويز جينيريتور)
 This model is a fine-tuned version of Mistral, specifically optimized for generating quizzes, exams, and educational questions based on given prompts or contexts.

 ---
 language:
+  - ar
+  - en
+license: apache-2.0
+library_name: transformers
 base_model: mistralai/Mistral-7B-v0.1
 pipeline_tag: text-generation
 tags:
+  - quiz-generator
+  - exam-generator
+  - educational
+inference: true
+widget:
+  - text: "Generate 3 MCQ questions about dental caries with answers."
 ---
 # Mistral Exam Generator (كويز جينيريتور)
 This model is a fine-tuned version of Mistral, specifically optimized for generating quizzes, exams, and educational questions based on given prompts or contexts.