Instructions to use grichard99/statpredict-lite with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use grichard99/statpredict-lite with Transformers:

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

pipe = pipeline("text-generation", model="grichard99/statpredict-lite")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("grichard99/statpredict-lite")
model = AutoModelForCausalLM.from_pretrained("grichard99/statpredict-lite", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use grichard99/statpredict-lite with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "grichard99/statpredict-lite"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "grichard99/statpredict-lite",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/grichard99/statpredict-lite

SGLang

How to use grichard99/statpredict-lite 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 "grichard99/statpredict-lite" \
    --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": "grichard99/statpredict-lite",
		"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 "grichard99/statpredict-lite" \
        --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": "grichard99/statpredict-lite",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use grichard99/statpredict-lite with Docker Model Runner:
```
docker model run hf.co/grichard99/statpredict-lite
```

grichard99 commited on Jul 20

Commit

dc008d3

verified ·

1 Parent(s): 04372bd

Revert to markdown link (HF sanitizes target attributes)

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -133,7 +133,7 @@ arbitrary multi digit merges. Training used early stopping on a held out validat
 **partitioned by athlete**, so no athlete appears in both train and validation.
 Full training recipe, data preparation scripts, and evaluation harness:
-<a href="https://github.com/grichard99/statpredict-lite" target="_blank" rel="noopener"><b>github.com/grichard99/statpredict-lite</b></a>
 ## Training data

 **partitioned by athlete**, so no athlete appears in both train and validation.
 Full training recipe, data preparation scripts, and evaluation harness:
+**[github.com/grichard99/statpredict-lite](https://github.com/grichard99/statpredict-lite)**
 ## Training data