Instructions to use STEM-AI-mtl/phi-2-electrical-engineering with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use STEM-AI-mtl/phi-2-electrical-engineering with Transformers:

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

pipe = pipeline("text-generation", model="STEM-AI-mtl/phi-2-electrical-engineering", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("STEM-AI-mtl/phi-2-electrical-engineering", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("STEM-AI-mtl/phi-2-electrical-engineering", trust_remote_code=True)

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use STEM-AI-mtl/phi-2-electrical-engineering with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/STEM-AI-mtl/phi-2-electrical-engineering

SGLang

How to use STEM-AI-mtl/phi-2-electrical-engineering 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 "STEM-AI-mtl/phi-2-electrical-engineering" \
    --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": "STEM-AI-mtl/phi-2-electrical-engineering",
		"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 "STEM-AI-mtl/phi-2-electrical-engineering" \
        --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": "STEM-AI-mtl/phi-2-electrical-engineering",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use STEM-AI-mtl/phi-2-electrical-engineering with Docker Model Runner:
```
docker model run hf.co/STEM-AI-mtl/phi-2-electrical-engineering
```

STEM-AI-mtl commited on Jan 7, 2024

Commit

351c0b8

1 Parent(s): cd0f87b

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -2

README.md CHANGED Viewed

@@ -39,7 +39,7 @@ Combined with
 Dataset related to STEM and NLP: garage-bAInd/Open-Platypus
 ### Training Procedure
-LoRa script:  https://github.com/STEM-ai/Phi-2/blob/4eaa6aaa2679427a810ace5a061b9c951942d66a/LoRa.py
 A LoRa PEFT was performed on a 48 Gb A40 Nvidia GPU.
@@ -50,4 +50,6 @@ William Harbec
 ### Inference example
-https://github.com/STEM-ai/Phi-2/blob/4eaa6aaa2679427a810ace5a061b9c951942d66a/chat.py

 Dataset related to STEM and NLP: garage-bAInd/Open-Platypus
 ### Training Procedure
+LoRa script:  https://github.com/STEM-ai/Phi-2/raw/4eaa6aaa2679427a810ace5a061b9c951942d66a/LoRa.py
 A LoRa PEFT was performed on a 48 Gb A40 Nvidia GPU.
 ### Inference example
+Standard: https://github.com/STEM-ai/Phi-2/raw/4eaa6aaa2679427a810ace5a061b9c951942d66a/chat.py
+GPTQ format: https://github.com/STEM-ai/Phi-2/raw/ab1ced8d7922765344d824acf1924df99606b4fc/chat-GPTQ.py