google/air_dialogue
Viewer • Updated • 724k • 336 • 22
How to use kaipybara/hackping-2025 with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="kaipybara/hackping-2025") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("kaipybara/hackping-2025")
model = AutoModelForCausalLM.from_pretrained("kaipybara/hackping-2025")How to use kaipybara/hackping-2025 with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kaipybara/hackping-2025"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "kaipybara/hackping-2025",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/kaipybara/hackping-2025
How to use kaipybara/hackping-2025 with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "kaipybara/hackping-2025" \
--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": "kaipybara/hackping-2025",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'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 "kaipybara/hackping-2025" \
--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": "kaipybara/hackping-2025",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use kaipybara/hackping-2025 with Docker Model Runner:
docker model run hf.co/kaipybara/hackping-2025
This is a test model uploaded for Hackping 2025.
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("kaipybara/hackping-2025")
model = AutoModelForCausalLM.from_pretrained("kaipybara/hackping-2025")
input_text = "Hello, my name is"
inputs = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**inputs)
print(tokenizer.decode(outputs[0]))
Base model
meta-llama/Llama-3.2-3B