Instructions to use anas-awadalla/opt-125m-squad with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use anas-awadalla/opt-125m-squad with Transformers:

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

pipe = pipeline("text-generation", model="anas-awadalla/opt-125m-squad")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("anas-awadalla/opt-125m-squad")
model = AutoModelForCausalLM.from_pretrained("anas-awadalla/opt-125m-squad")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use anas-awadalla/opt-125m-squad with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "anas-awadalla/opt-125m-squad"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "anas-awadalla/opt-125m-squad",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/anas-awadalla/opt-125m-squad

SGLang

How to use anas-awadalla/opt-125m-squad 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 "anas-awadalla/opt-125m-squad" \
    --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": "anas-awadalla/opt-125m-squad",
		"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 "anas-awadalla/opt-125m-squad" \
        --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": "anas-awadalla/opt-125m-squad",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use anas-awadalla/opt-125m-squad with Docker Model Runner:
```
docker model run hf.co/anas-awadalla/opt-125m-squad
```

anas-awadalla commited on May 19, 2022

Commit

d1b1d7d

1 Parent(s): 39a2fc5

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -1,4 +1,4 @@
-An OPT-125M model trained on SQUAD for extractive question answering reaching validation F1 performance of ~78.
 To use the model format input in the following manner:


1	+ A facebook/opt-125m model trained on SQUAD for extractive question answering reaching validation F1 performance of ~78.
2
3	To use the model format input in the following manner:
4