Instructions to use ccore/opt-350m-open-data-understanding with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ccore/opt-350m-open-data-understanding with Transformers:

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

pipe = pipeline("text-generation", model="ccore/opt-350m-open-data-understanding")

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

tokenizer = AutoTokenizer.from_pretrained("ccore/opt-350m-open-data-understanding")
model = AutoModelForCausalLM.from_pretrained("ccore/opt-350m-open-data-understanding", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ccore/opt-350m-open-data-understanding with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ccore/opt-350m-open-data-understanding"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ccore/opt-350m-open-data-understanding",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ccore/opt-350m-open-data-understanding

SGLang

How to use ccore/opt-350m-open-data-understanding 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 "ccore/opt-350m-open-data-understanding" \
    --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": "ccore/opt-350m-open-data-understanding",
		"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 "ccore/opt-350m-open-data-understanding" \
        --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": "ccore/opt-350m-open-data-understanding",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ccore/opt-350m-open-data-understanding with Docker Model Runner:
```
docker model run hf.co/ccore/opt-350m-open-data-understanding
```

ccore commited on Sep 26, 2023

Commit

68bb1de

1 Parent(s): 2285e94

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -3

README.md CHANGED Viewed

@@ -8,9 +8,8 @@ tags:
 - opt
 metrics:
 - accuracy
-model-index:
-- name: mini3
-  results: []
 datasets:
 - ccore/open_data_understanding
 pipeline_tag: text-generation

 - opt
 metrics:
 - accuracy
+widget:
+- text: "Certainly! Consider a user interface for a complex software application. If the user encounters a lengthy list of commands or prompts, it could lead to confusion and frustration. By limiting the number of tokens, the model can provide concise instructions that are easy to understand, leading to a smoother user experience.\n\n# [UNDERSTANDING]\n"
 datasets:
 - ccore/open_data_understanding
 pipeline_tag: text-generation