Instructions to use Haskar/mistral-programming-tutor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Haskar/mistral-programming-tutor with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Haskar/mistral-programming-tutor")
model = AutoModelForCausalLM.from_pretrained("Haskar/mistral-programming-tutor", 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 Haskar/mistral-programming-tutor with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Haskar/mistral-programming-tutor

SGLang

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

Docker Model Runner
How to use Haskar/mistral-programming-tutor with Docker Model Runner:
```
docker model run hf.co/Haskar/mistral-programming-tutor
```

Mistral Programming Tutor (Fine-Tuned)

Overview

This model is a fine-tuned version of Mistral-7B-Instruct designed to act as a Programming Tutor.

It provides structured teaching responses instead of direct answers.

Objective

Build an AI tutor that:

Explains concepts step-by-step
Uses a consistent teaching format
Asks checkpoint questions
Stays within programming domain

Model Details

Base Model: mistralai/Mistral-7B-Instruct-v0.1
Fine-tuning: QLoRA (4-bit)
Framework: Transformers + TRL + PEFT
Task: Instruction-following Programming Tutor

Response Format

The model follows a strict structure:

Goal: Explanation: Steps: Code: Example: Checkpoint Question:

Example Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("Haskar/mistral-programming-tutor")
tokenizer = AutoTokenizer.from_pretrained("Haskar/mistral-programming-tutor")

prompt = """### Instruction:
Explain recursion in Python

### Response:
Goal:
"""

inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=200)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Downloads last month: 20

Safetensors

Model size

7B params

Tensor type

F32

BF16

F16