croqaz/Sprocket-n-Say
Viewer • Updated • 15M • 133 • 1
How to use croqaz/Sprocket-and-Say with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="croqaz/Sprocket-and-Say") # Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("croqaz/Sprocket-and-Say", device_map="auto")How to use croqaz/Sprocket-and-Say with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "croqaz/Sprocket-and-Say"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "croqaz/Sprocket-and-Say",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/croqaz/Sprocket-and-Say
How to use croqaz/Sprocket-and-Say with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "croqaz/Sprocket-and-Say" \
--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": "croqaz/Sprocket-and-Say",
"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 "croqaz/Sprocket-and-Say" \
--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": "croqaz/Sprocket-and-Say",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use croqaz/Sprocket-and-Say with Docker Model Runner:
docker model run hf.co/croqaz/Sprocket-and-Say
I've no pulse, no nerves, no need for tea, I'll argue physics or flatter thee. Feed me questions, feed me spite - I'll strike you dumb or strike you bright. No tongue to tire, no need to pray - Turn the crank. Sprocket & Say.
WIP, the model is still training. The latest checkpoints are the 2 "time 40h" folders.
This is a tiny hobby LLM built by one guy, on one medium-budget gaming PC with one GPU.
Don't expect miracles.
It is pretty good tho.