Instructions to use AlanRobotics/opt-assisted-generation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AlanRobotics/opt-assisted-generation with Transformers:

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

pipe = pipeline("text-generation", model="AlanRobotics/opt-assisted-generation")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AlanRobotics/opt-assisted-generation")
model = AutoModelForCausalLM.from_pretrained("AlanRobotics/opt-assisted-generation")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AlanRobotics/opt-assisted-generation with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AlanRobotics/opt-assisted-generation

SGLang

How to use AlanRobotics/opt-assisted-generation 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 "AlanRobotics/opt-assisted-generation" \
    --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": "AlanRobotics/opt-assisted-generation",
		"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 "AlanRobotics/opt-assisted-generation" \
        --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": "AlanRobotics/opt-assisted-generation",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AlanRobotics/opt-assisted-generation with Docker Model Runner:
```
docker model run hf.co/AlanRobotics/opt-assisted-generation
```

AlanRobotics commited on Oct 16, 2023

Commit

c22f9cb

1 Parent(s): bdcbfc1

Training in progress, step 8200

Browse files

Files changed (1) hide show

pytorch_model.bin +1 -1

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81f9ac7e091517eb744e0f5714787d055664c77206152f4e731e1d207c50b8eb
 size 444891805

 version https://git-lfs.github.com/spec/v1
+oid sha256:8e0183a13bf927a8559da52e9ec291f935e5ab35f7eb436d9b5c0b4fba24c2d5
 size 444891805