Instructions to use akoksal/LongForm-OPT-2.7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use akoksal/LongForm-OPT-2.7B with Transformers:

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

pipe = pipeline("text-generation", model="akoksal/LongForm-OPT-2.7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("akoksal/LongForm-OPT-2.7B")
model = AutoModelForCausalLM.from_pretrained("akoksal/LongForm-OPT-2.7B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use akoksal/LongForm-OPT-2.7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "akoksal/LongForm-OPT-2.7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "akoksal/LongForm-OPT-2.7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/akoksal/LongForm-OPT-2.7B

SGLang

How to use akoksal/LongForm-OPT-2.7B 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 "akoksal/LongForm-OPT-2.7B" \
    --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": "akoksal/LongForm-OPT-2.7B",
		"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 "akoksal/LongForm-OPT-2.7B" \
        --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": "akoksal/LongForm-OPT-2.7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use akoksal/LongForm-OPT-2.7B with Docker Model Runner:
```
docker model run hf.co/akoksal/LongForm-OPT-2.7B
```

LongForm-OPT-2.7B

Commit History

Update README.md

bd599d0
verified

akoksal commited on Mar 5, 2024

Update README.md

dfb2a7e
verified

akoksal commited on Mar 5, 2024

Update README.md

3ee8c4f

akoksal commited on May 23, 2023

Update README.md

032665d

akoksal commited on Apr 26, 2023

Update README.md

77f68ce

akoksal commited on Apr 26, 2023

Update README.md

a820aca

akoksal commited on Apr 26, 2023

Update README.md

2649f69

akoksal commited on Apr 26, 2023

Adding `safetensors` variant of this model (#1)

0b718d9

akoksal

SFconvertbot commited on Apr 18, 2023

Update README.md

2a0dfd9

akoksal commited on Apr 17, 2023

Update README.md

828203a

akoksal commited on Apr 17, 2023

Update README.md

4544673

akoksal commited on Apr 17, 2023

Update README.md

47f2b12

akoksal commited on Apr 17, 2023

Update README.md

e90cc8c

akoksal commited on Apr 17, 2023

Update README.md

27da398

akoksal commited on Apr 16, 2023

Update README.md

0c52000

akoksal commited on Apr 16, 2023