Instructions to use MayaPH/FinOPT-Washington with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MayaPH/FinOPT-Washington with Transformers:

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

pipe = pipeline("text-generation", model="MayaPH/FinOPT-Washington")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MayaPH/FinOPT-Washington")
model = AutoModelForCausalLM.from_pretrained("MayaPH/FinOPT-Washington", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MayaPH/FinOPT-Washington with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/MayaPH/FinOPT-Washington

SGLang

How to use MayaPH/FinOPT-Washington 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 "MayaPH/FinOPT-Washington" \
    --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": "MayaPH/FinOPT-Washington",
		"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 "MayaPH/FinOPT-Washington" \
        --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": "MayaPH/FinOPT-Washington",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MayaPH/FinOPT-Washington with Docker Model Runner:
```
docker model run hf.co/MayaPH/FinOPT-Washington
```

FinOPT-Washington

Commit History

Jun 1, 2023

14:00
Adding `safetensors` variant of this model⁠

SFconvertbot

1da28bc
12:44
Update README.md

jaspercatapang

ffe268e
11:14
Update README.md

jaspercatapang

3f44e4f

May 27, 2023

19:34
Update README.md

jaspercatapang

29de03a
19:33
Update README.md

jaspercatapang

623116e

May 26, 2023

18:08
Update README.md

jaspercatapang

fff6602
18:07
Update README.md⁠

jaspercatapang

a797b02
17:57
Create README.md⁠

jaspercatapang

1cf36b2
17:22
Upload tokenizer

jaspercatapang

5cead53
17:17
Upload tokenizer

jaspercatapang

5022707
17:12
Upload OPTForCausalLM

jaspercatapang

fdd4c93
17:11
initial commit

Jasper Kyle Catapang

ea604ac

Commit History

Jun 1, 2023

Adding `safetensors` variant of this model⁠

Update README.md

Update README.md

May 27, 2023

Update README.md

Update README.md

May 26, 2023

Update README.md

Update README.md⁠

Create README.md⁠

Upload tokenizer

Upload tokenizer

Upload OPTForCausalLM

initial commit