Instructions to use dlowl/dolly-v2-3b-endpoint with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dlowl/dolly-v2-3b-endpoint with Transformers:

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

pipe = pipeline("text-generation", model="dlowl/dolly-v2-3b-endpoint")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dlowl/dolly-v2-3b-endpoint")
model = AutoModelForCausalLM.from_pretrained("dlowl/dolly-v2-3b-endpoint", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dlowl/dolly-v2-3b-endpoint with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dlowl/dolly-v2-3b-endpoint"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dlowl/dolly-v2-3b-endpoint",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/dlowl/dolly-v2-3b-endpoint

SGLang

How to use dlowl/dolly-v2-3b-endpoint 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 "dlowl/dolly-v2-3b-endpoint" \
    --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": "dlowl/dolly-v2-3b-endpoint",
		"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 "dlowl/dolly-v2-3b-endpoint" \
        --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": "dlowl/dolly-v2-3b-endpoint",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use dlowl/dolly-v2-3b-endpoint with Docker Model Runner:
```
docker model run hf.co/dlowl/dolly-v2-3b-endpoint
```

Update README.md

by cherry0328 - opened Jan 7

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

-0

cherry0328

Jan 7

The dolly-v2-3b model is truly impressive in its instruction-following capabilities. We would love to contribute by updating the README to include accurate information about the base model. This effort aims to enhance the completeness of the model card. Thank you !

Update README.md0baca6fc

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment