Instructions to use impactframes/IF-PromptMKR-phi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use impactframes/IF-PromptMKR-phi with Transformers:

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

pipe = pipeline("text-generation", model="impactframes/IF-PromptMKR-phi", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("impactframes/IF-PromptMKR-phi", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use impactframes/IF-PromptMKR-phi with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/impactframes/IF-PromptMKR-phi

SGLang

How to use impactframes/IF-PromptMKR-phi 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 "impactframes/IF-PromptMKR-phi" \
    --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": "impactframes/IF-PromptMKR-phi",
		"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 "impactframes/IF-PromptMKR-phi" \
        --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": "impactframes/IF-PromptMKR-phi",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use impactframes/IF-PromptMKR-phi with Docker Model Runner:
```
docker model run hf.co/impactframes/IF-PromptMKR-phi
```

impactframes commited on Oct 1, 2023

Commit

b93aea5

1 Parent(s): e37072e

Create README.md

Browse files

Files changed (1) hide show

README.md +17 -0

README.md ADDED Viewed

	@@ -0,0 +1,17 @@

+### License
+The model is licensed under the [Research License](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx).
+Model is a qlora of the IFprompMKR dataset base of https://huggingface.co/microsoft/phi-1_5
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/63c2c05b8cc87cf0c05b89ba/2yqHGFpLXdyH5DY3jDH5Z.png)
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/63c2c05b8cc87cf0c05b89ba/BpmSdSLKiF0iSz-PW-t1z.png)
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/63c2c05b8cc87cf0c05b89ba/eBwiOKS1XF2MM2fbqMfeL.png)
+Not sure how well will work with the prompt MKR but most likely it will need these settings