Instructions to use Yasir-khan/Recipe-Using-GPT2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Yasir-khan/Recipe-Using-GPT2 with Transformers:

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

pipe = pipeline("text-generation", model="Yasir-khan/Recipe-Using-GPT2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Yasir-khan/Recipe-Using-GPT2")
model = AutoModelForCausalLM.from_pretrained("Yasir-khan/Recipe-Using-GPT2")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Yasir-khan/Recipe-Using-GPT2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Yasir-khan/Recipe-Using-GPT2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Yasir-khan/Recipe-Using-GPT2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Yasir-khan/Recipe-Using-GPT2

SGLang

How to use Yasir-khan/Recipe-Using-GPT2 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 "Yasir-khan/Recipe-Using-GPT2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Yasir-khan/Recipe-Using-GPT2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Yasir-khan/Recipe-Using-GPT2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Yasir-khan/Recipe-Using-GPT2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Yasir-khan/Recipe-Using-GPT2 with Docker Model Runner:
```
docker model run hf.co/Yasir-khan/Recipe-Using-GPT2
```

Yasir-khan commited on Jul 23, 2024

Commit

107cf95

verified ·

1 Parent(s): db4edb3

Create README.md

Browse files

Files changed (1) hide show

README.md +13 -0

README.md ADDED Viewed

	@@ -0,0 +1,13 @@

+I want to finetune a Generative AI Model that takes ingredients as input and generate an accurate recipe specific to the Indian cuisine.
+Finetuning a generation model to be able to generate accurate recipes about a particular dish specific to your cuisine.
+There is an existing dataset available on Kaggle which I used to extract some of the samples. I used this particular dataset because
+it fulfills my requirements of including Indian cuisine for recipe generation. The dataset contained cuisines from various cultures,
+but I extracted only the samples specific to Indian cuisine.
+I have extracted more than 600 samples from the dataset. I also performed comprehensive data analysis to check for incorrect,
+incomprehensible, irrelavant data. I removed the irrelevant features, duplicate values, and samples that were in languages other than English.
+I imputated the null values as there were less number of fields. Similarly, I cleaned the text from extra spaces. In order to
+make sure diversity of the dataset, I included course and diet fields which make the data more diverse.