Instructions to use TuringsSolutions/PFAFphi-750 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TuringsSolutions/PFAFphi-750 with Transformers:

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

pipe = pipeline("text-generation", model="TuringsSolutions/PFAFphi-750", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TuringsSolutions/PFAFphi-750", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("TuringsSolutions/PFAFphi-750", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TuringsSolutions/PFAFphi-750 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TuringsSolutions/PFAFphi-750"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TuringsSolutions/PFAFphi-750",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TuringsSolutions/PFAFphi-750

SGLang

How to use TuringsSolutions/PFAFphi-750 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 "TuringsSolutions/PFAFphi-750" \
    --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": "TuringsSolutions/PFAFphi-750",
		"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 "TuringsSolutions/PFAFphi-750" \
        --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": "TuringsSolutions/PFAFphi-750",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TuringsSolutions/PFAFphi-750 with Docker Model Runner:
```
docker model run hf.co/TuringsSolutions/PFAFphi-750
```

TuringsSolutions commited on Jan 18, 2024

Commit

a451fa5

verified ·

1 Parent(s): d7c7863

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -0

README.md CHANGED Viewed

@@ -3,6 +3,9 @@ license: mit
 datasets:
 - TuringsSolutions/PFAF750
 ---
 Model Responses:
 Please create a short fictional story

 datasets:
 - TuringsSolutions/PFAF750
 ---
+PFAFphi-750 was fine tuned for 30 minutes on a single T4 GPU
+3 Epochs total
 Model Responses:
 Please create a short fictional story