Instructions to use Cohee/fooocus_expansion-onnx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Cohee/fooocus_expansion-onnx with Transformers:

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

pipe = pipeline("text-generation", model="Cohee/fooocus_expansion-onnx")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Cohee/fooocus_expansion-onnx")
model = AutoModelForCausalLM.from_pretrained("Cohee/fooocus_expansion-onnx")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Cohee/fooocus_expansion-onnx with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Cohee/fooocus_expansion-onnx

SGLang

How to use Cohee/fooocus_expansion-onnx 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 "Cohee/fooocus_expansion-onnx" \
    --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": "Cohee/fooocus_expansion-onnx",
		"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 "Cohee/fooocus_expansion-onnx" \
        --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": "Cohee/fooocus_expansion-onnx",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Cohee/fooocus_expansion-onnx with Docker Model Runner:
```
docker model run hf.co/Cohee/fooocus_expansion-onnx
```

Cohee commited on Oct 20, 2023

Commit

42d2716

1 Parent(s): c89844b

Upload 6 files

Browse files

Files changed (6) hide show

onnx/decoder_model.onnx +2 -2
onnx/decoder_model_merged.onnx +2 -2
onnx/decoder_model_merged_quantized.onnx +2 -2
onnx/decoder_model_quantized.onnx +2 -2
onnx/decoder_with_past_model.onnx +2 -2
onnx/decoder_with_past_model_quantized.onnx +2 -2

onnx/decoder_model.onnx CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87e979f4e6f2b07cb9ac47e893e2c53f5fe58f503ae38f5ff90704f0197851bf
-size 499275976

 version https://git-lfs.github.com/spec/v1
+oid sha256:05d077640e259e7dee0a02fec0f85db50556643f71dc999f7c48858c9bb4c554
+size 499207554

onnx/decoder_model_merged.onnx CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a955365080142a0c21abc3e2578fcf6418588bb914358ba975fc7d837daf46a
-size 500799139

 version https://git-lfs.github.com/spec/v1
+oid sha256:81d09a92266c988a4960b9b3f188d51dff04259c163b6a0d4c14d08b4fb4da1a
+size 500662142

onnx/decoder_model_merged_quantized.onnx CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca94b8367d0aec480e1a83f7146121c743c6154f7cf16cc4f43cf41e560d9bd4
-size 128315766

 version https://git-lfs.github.com/spec/v1
+oid sha256:16f147115539022ab52f075178a7563c39aa5d61d3dc79590729d56884afd59d
+size 128048017

onnx/decoder_model_quantized.onnx CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30372fe03f412a34a167947a326ecaba37065d27470656c107b871157aeaf19f
-size 126556880

 version https://git-lfs.github.com/spec/v1
+oid sha256:c39b2267a42c786cef504041aa3f64648f7689c49cb9830f68b712796aeec4df
+size 126423159

onnx/decoder_with_past_model.onnx CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9849bb4dab43c80c0a14b72f9d26931d9cddafdf68c1145b608c7dedc55e2d8d
-size 499282782

 version https://git-lfs.github.com/spec/v1
+oid sha256:5a24edaa1d7436429bbce7c381b4c70f3db168ab858e085b62703e0dc4bb87a9
+size 499214209

onnx/decoder_with_past_model_quantized.onnx CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d71976e10aff4b54827978751e684872bad5a0e33dafc4c63980739a5555d25b
-size 126565928

 version https://git-lfs.github.com/spec/v1
+oid sha256:f31df3fbd6b298657e85bf58b69f146789ccfc850711ccee02b6e98b488ea34c
+size 126431902