Instructions to use acul3/dalle-mini-indo-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use acul3/dalle-mini-indo-base with Transformers:

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

pipe = pipeline("text-generation", model="acul3/dalle-mini-indo-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("acul3/dalle-mini-indo-base")
model = AutoModelForSeq2SeqLM.from_pretrained("acul3/dalle-mini-indo-base")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use acul3/dalle-mini-indo-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "acul3/dalle-mini-indo-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "acul3/dalle-mini-indo-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/acul3/dalle-mini-indo-base

SGLang

How to use acul3/dalle-mini-indo-base 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 "acul3/dalle-mini-indo-base" \
    --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": "acul3/dalle-mini-indo-base",
		"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 "acul3/dalle-mini-indo-base" \
        --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": "acul3/dalle-mini-indo-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use acul3/dalle-mini-indo-base with Docker Model Runner:
```
docker model run hf.co/acul3/dalle-mini-indo-base
```

acul3 commited on Aug 6, 2021

Commit

43d2610

1 Parent(s): 85d639f

last epoch

Browse files

Files changed (3) hide show

flax_model.msgpack +1 -1
opt_state.msgpack +1 -1
training_state.json +1 -1

flax_model.msgpack CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88e678d8d9f1b830276ef564deb9cee2d14851b3c7ad41dc7ff6832c8d1de3e8
 size 992295891

 version https://git-lfs.github.com/spec/v1
+oid sha256:e90682453359691b3f67e912ce02dbbf43d051a258ae94bfc8dec8791a97470c
 size 992295891

opt_state.msgpack CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a67679b73443ab419969dcb0b79cba19e0068fbb416930751e61f316bce1601
 size 2200476

 version https://git-lfs.github.com/spec/v1
+oid sha256:f771a8abdf7b1a4e5ba20333c991b12745e1c33e9aed9e6457c97332aa0ca9ee
 size 2200476

training_state.json CHANGED Viewed

	@@ -1 +1 @@
1	- {"step": ~~322110~~}


1	+ {"step": 386532}