Instructions to use PingVortex/Youtube-shorts-comment-generator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PingVortex/Youtube-shorts-comment-generator with Transformers:

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

pipe = pipeline("text-generation", model="PingVortex/Youtube-shorts-comment-generator")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PingVortex/Youtube-shorts-comment-generator")
model = AutoModelForCausalLM.from_pretrained("PingVortex/Youtube-shorts-comment-generator")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use PingVortex/Youtube-shorts-comment-generator with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/PingVortex/Youtube-shorts-comment-generator

SGLang

How to use PingVortex/Youtube-shorts-comment-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 "PingVortex/Youtube-shorts-comment-generator" \
    --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": "PingVortex/Youtube-shorts-comment-generator",
		"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 "PingVortex/Youtube-shorts-comment-generator" \
        --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": "PingVortex/Youtube-shorts-comment-generator",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use PingVortex/Youtube-shorts-comment-generator with Docker Model Runner:
```
docker model run hf.co/PingVortex/Youtube-shorts-comment-generator
```

PingVortex commited on Mar 5

Commit

1a76289

verified ·

1 Parent(s): 2c5af53

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -23

README.md CHANGED Viewed

@@ -20,21 +20,17 @@ pipeline_tag: text-generation
 library_name: transformers
 ---
-# Youtube shorts comment generator 🧠 (I couldn't come up with a more original name)
-A **fine-tuned DistilGPT2 model** trained on 1.4M+ YouTube Shorts comments - the perfect language model for generating cursed internet humor, emoji spam, and authentic YouTube degeneracy.
 - Base model: [distilgpt2](https://huggingface.co/distilgpt2)
 - Trained on: [YouTube Shorts Comments Dataset](https://huggingface.co/datasets/PingVortex/Youtube_shorts_comments)
-- Creator: [PingVortex](https://github.com/PingVortex)
-## Model Details 🔥
 - **Parameters**: 82M (DistilGPT2 architecture)
 - **Training Data**: 1,475,500 YouTube Shorts comments
-- **Special Skills**: Emoji generation, broken English, random character generation
-## Usage Example 🐍
 ```python
 from transformers import pipeline
@@ -48,24 +44,10 @@ print(output[0]['generated_text'])
 *Sample output:*
 `"When you see a Sigma edit: 😂😂😂😂 The white one on the last pic?😂😂😂😅😅😅😊😊😊😅😮😮😅"`
-## Training Info ⚙️
 - **Epochs**: 1
 - **Batch Size**: 8
 - **Hardware**: Google Colab T4 GPU
 - **Training Time**: ~2 hours
-- **Loss**: 0.24
-## Ethical Considerations ⚠️
-This model may generate:
-- Extreme emoji spam (🔥💀🤣)
-- Nonsensical combinations
-- Mild brain damage
-- Occasional coherent text
-Use responsibly (or irresponsibly, we don't judge).
-## License 📜
-**CC0 1.0 Universal** (Public Domain)

 library_name: transformers
 ---
+# Youtube shorts comment generator
 - Base model: [distilgpt2](https://huggingface.co/distilgpt2)
 - Trained on: [YouTube Shorts Comments Dataset](https://huggingface.co/datasets/PingVortex/Youtube_shorts_comments)
+## Model Details
 - **Parameters**: 82M (DistilGPT2 architecture)
 - **Training Data**: 1,475,500 YouTube Shorts comments
+## Usage Example
 ```python
 from transformers import pipeline
 *Sample output:*
 `"When you see a Sigma edit: 😂😂😂😂 The white one on the last pic?😂😂😂😅😅😅😊😊😊😅😮😮😅"`
+## Training Info
 - **Epochs**: 1
 - **Batch Size**: 8
 - **Hardware**: Google Colab T4 GPU
 - **Training Time**: ~2 hours
+- **Loss**: 0.24