Instructions to use x5tne/playdate-distilgpt2-5k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use x5tne/playdate-distilgpt2-5k with Transformers:

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

pipe = pipeline("text-generation", model="x5tne/playdate-distilgpt2-5k")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("x5tne/playdate-distilgpt2-5k")
model = AutoModelForMultimodalLM.from_pretrained("x5tne/playdate-distilgpt2-5k")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use x5tne/playdate-distilgpt2-5k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "x5tne/playdate-distilgpt2-5k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "x5tne/playdate-distilgpt2-5k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/x5tne/playdate-distilgpt2-5k

SGLang

How to use x5tne/playdate-distilgpt2-5k 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 "x5tne/playdate-distilgpt2-5k" \
    --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": "x5tne/playdate-distilgpt2-5k",
		"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 "x5tne/playdate-distilgpt2-5k" \
        --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": "x5tne/playdate-distilgpt2-5k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use x5tne/playdate-distilgpt2-5k with Docker Model Runner:
```
docker model run hf.co/x5tne/playdate-distilgpt2-5k
```

Playdate DistilGPT2: 5k Samples

Expect this to be the last model based on DistilGPT2 as coherence has not advanced. Test model for newer personalities, not to be used in production. Script example below.

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MODEL_PATH = "x5tne/playdate-distilgpt2-5k" 

# Load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
model = AutoModelForCausalLM.from_pretrained(MODEL_PATH)
model.eval()

# Example prompt
prompt = """<system harsh>
<summary>none</summary>
<user>Hi [namehere]! How are you today?</user>
<assistant>"""

# Encode input
inputs = tokenizer(prompt, return_tensors="pt")

# Generate output
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=100,
        do_sample=True,
        temperature=0.9,
        top_p=0.9,
        repetition_penalty=1.15
    )

# Decode generated tokens
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)

print("Assistant response:")
print(response)