Instructions to use BricksDisplay/phi-2-qnn with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BricksDisplay/phi-2-qnn with Transformers:

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

pipe = pipeline("text-generation", model="BricksDisplay/phi-2-qnn", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BricksDisplay/phi-2-qnn", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("BricksDisplay/phi-2-qnn", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use BricksDisplay/phi-2-qnn with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BricksDisplay/phi-2-qnn"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BricksDisplay/phi-2-qnn",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/BricksDisplay/phi-2-qnn

SGLang

How to use BricksDisplay/phi-2-qnn 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 "BricksDisplay/phi-2-qnn" \
    --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": "BricksDisplay/phi-2-qnn",
		"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 "BricksDisplay/phi-2-qnn" \
        --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": "BricksDisplay/phi-2-qnn",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use BricksDisplay/phi-2-qnn with Docker Model Runner:
```
docker model run hf.co/BricksDisplay/phi-2-qnn
```

hans00 commited on Apr 11, 2024

Commit

4bee4ac

verified ·

1 Parent(s): 7f7154f

Upload folder using huggingface_hub

Browse files

Files changed (3) hide show

onnx/decoder_model_merged_quantized.onnx +2 -2
onnx/decoder_model_quantized.onnx +2 -2
onnx/decoder_model_quantized.onnx_data +2 -2

onnx/decoder_model_merged_quantized.onnx CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d2d4d4fbe9a3f66beb94322adcd9e25358db6a365ec739c5a19245d17fb68ea
-size 3189949

 version https://git-lfs.github.com/spec/v1
+oid sha256:f063f8e92c4f8ae6b4480e3486fc5f02245a7f26cf3cfc01926c3957b4dfe483
+size 3350547

onnx/decoder_model_quantized.onnx CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb40c9d3e66c2f0c651959eb60028acbf731bf39cc035809343b6e1e11e56c39
-size 3672026

 version https://git-lfs.github.com/spec/v1
+oid sha256:07276362da3408bf434feb87aff899dda6066323b1c02883f641947d9b9edc60
+size 4032485

onnx/decoder_model_quantized.onnx_data CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:965d152e98a0dbc440fa9eecaa8a9409e623e44693de200ae93f9eefd1bebd9e
-size 2912322048

 version https://git-lfs.github.com/spec/v1
+oid sha256:56d941cce025a5a2f5a3a6247c4e52e43760407a5b2df1e2e2199177fbd60fa5
+size 2912237568