Instructions to use gr0010/ArtificialThinker-Phi2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gr0010/ArtificialThinker-Phi2 with Transformers:

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

pipe = pipeline("text-generation", model="gr0010/ArtificialThinker-Phi2", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("gr0010/ArtificialThinker-Phi2", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use gr0010/ArtificialThinker-Phi2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gr0010/ArtificialThinker-Phi2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gr0010/ArtificialThinker-Phi2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/gr0010/ArtificialThinker-Phi2

SGLang

How to use gr0010/ArtificialThinker-Phi2 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 "gr0010/ArtificialThinker-Phi2" \
    --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": "gr0010/ArtificialThinker-Phi2",
		"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 "gr0010/ArtificialThinker-Phi2" \
        --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": "gr0010/ArtificialThinker-Phi2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use gr0010/ArtificialThinker-Phi2 with Docker Model Runner:
```
docker model run hf.co/gr0010/ArtificialThinker-Phi2
```

No Longer Working

by mrfakename - opened Jan 14, 2024

Discussion

mrfakename

Jan 14, 2024

Hi,
Phi 2 changed their tensor names so the custom code is now aligned to the new tensors.
A solution to this is to upload the custom code of the original version of the Phi 2 model.
Thank you!

freeCS-dot-org

Jan 14, 2024

Thank you for the info, I fixed it, now it should work.

mrfakename

Jan 14, 2024

Thanks! Restarted the demo

mrfakename

Jan 14, 2024

Works now!

mrfakename changed discussion status to closed Jan 14, 2024

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment