Instructions to use afzalur/case-study-mistral-7b-full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use afzalur/case-study-mistral-7b-full with Transformers:

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

pipe = pipeline("text-generation", model="afzalur/case-study-mistral-7b-full")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("afzalur/case-study-mistral-7b-full")
model = AutoModelForCausalLM.from_pretrained("afzalur/case-study-mistral-7b-full")
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 afzalur/case-study-mistral-7b-full with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "afzalur/case-study-mistral-7b-full"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "afzalur/case-study-mistral-7b-full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/afzalur/case-study-mistral-7b-full

SGLang

How to use afzalur/case-study-mistral-7b-full 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 "afzalur/case-study-mistral-7b-full" \
    --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": "afzalur/case-study-mistral-7b-full",
		"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 "afzalur/case-study-mistral-7b-full" \
        --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": "afzalur/case-study-mistral-7b-full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use afzalur/case-study-mistral-7b-full with Docker Model Runner:
```
docker model run hf.co/afzalur/case-study-mistral-7b-full
```

🎓 Case Study Mistral 7B - Production Ready

A fine-tuned Mistral 7B model specialized for business case study generation.

🚀 Quick Start

Note: If the inference widget above shows "not deployed", use the code below for local testing:

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load model
model_name = "afzalur/case-study-mistral-7b-full"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.float16,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Generate case study
prompt = "Create a case study about sustainable business practices for an MBA course"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(
    **inputs, 
    max_new_tokens=512, 
    temperature=0.7,
    do_sample=True
)

result = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(result[len(prompt):])  # Only show generated content

🎯 Business Applications

Business Schools: Curriculum development
Corporate Training: Leadership scenarios
Consulting: Case study libraries
EdTech: Automated content generation

📊 Model Details

Base Model: Mistral 7B Instruct v0.3
Training: LoRA fine-tuning on business case studies
Context Length: 8K tokens
Model Size: ~13.5GB
Quality: Professional academic standard

💻 API Usage

# For programmatic access
from transformers import pipeline

generator = pipeline(
    "text-generation",
    model="afzalur/case-study-mistral-7b-full",
    torch_dtype=torch.float16,
    device_map="auto"
)

result = generator(
    "Create a case study about digital transformation",
    max_new_tokens=512,
    temperature=0.7
)
print(result[0]['generated_text'])