Instructions to use echarlaix/tiny-random-PhiForCausalLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use echarlaix/tiny-random-PhiForCausalLM with Transformers:

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

pipe = pipeline("text-generation", model="echarlaix/tiny-random-PhiForCausalLM")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("echarlaix/tiny-random-PhiForCausalLM")
model = AutoModelForCausalLM.from_pretrained("echarlaix/tiny-random-PhiForCausalLM")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use echarlaix/tiny-random-PhiForCausalLM with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/echarlaix/tiny-random-PhiForCausalLM

SGLang

How to use echarlaix/tiny-random-PhiForCausalLM 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 "echarlaix/tiny-random-PhiForCausalLM" \
    --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": "echarlaix/tiny-random-PhiForCausalLM",
		"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 "echarlaix/tiny-random-PhiForCausalLM" \
        --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": "echarlaix/tiny-random-PhiForCausalLM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use echarlaix/tiny-random-PhiForCausalLM with Docker Model Runner:
```
docker model run hf.co/echarlaix/tiny-random-PhiForCausalLM
```

echarlaix HF Staff commited on May 14, 2024

Commit

f047b61

verified ·

1 Parent(s): 67806c0

Adding OpenVINO file of this model (#1)

Browse files

- Adding OpenVINO file of this model (f5a0a2dc743c997c62454e9e1cde32930cace2c9)

Files changed (2) hide show

openvino_model.bin +3 -0
openvino_model.xml +0 -0

openvino_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:20fd0bbe41c621f8e9fbcc7c75592e9b431d39ab38604c9c9c891e2b12c2d4a9
+size 330488

openvino_model.xml ADDED Viewed

The diff for this file is too large to render. See raw diff