Instructions to use DisgustingOzil/Academic-MCQ-Generator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DisgustingOzil/Academic-MCQ-Generator with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("DisgustingOzil/Academic-MCQ-Generator", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Studio
How to use DisgustingOzil/Academic-MCQ-Generator with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for DisgustingOzil/Academic-MCQ-Generator to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for DisgustingOzil/Academic-MCQ-Generator to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for DisgustingOzil/Academic-MCQ-Generator to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="DisgustingOzil/Academic-MCQ-Generator", max_seq_length=2048, )
created handler.py
Browse files- handler.py +20 -0
handler.py
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from typing import Dict, List, Any
|
| 2 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 3 |
+
|
| 4 |
+
class EndpointHandler:
|
| 5 |
+
def __init__(self, path=""):
|
| 6 |
+
model_id = "DisgustingOzil/Academic-MCQ-Generator"
|
| 7 |
+
load_in_4bit = True
|
| 8 |
+
self.tokenizer = AutoTokenizer.from_pretrained(model_id)
|
| 9 |
+
self.model = AutoModelForCausalLM.from_pretrained(model_id, load_in_4bit=load_in_4bit)
|
| 10 |
+
|
| 11 |
+
def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
|
| 12 |
+
input_text = data.pop("input_text", data)
|
| 13 |
+
inputs = self.tokenizer(input_text, return_tensors="pt")
|
| 14 |
+
outputs = self.model.generate(
|
| 15 |
+
**inputs,
|
| 16 |
+
max_length=1000,
|
| 17 |
+
num_return_sequences=1,
|
| 18 |
+
)
|
| 19 |
+
output_text = self.tokenizer.decode(outputs[0], skip_special_tokens=True)
|
| 20 |
+
return [{"generated_text": output_text}]
|