Instructions to use umm-maybe/phi-1_5-finetuned-skip0clip with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use umm-maybe/phi-1_5-finetuned-skip0clip with Transformers:

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

pipe = pipeline("text-generation", model="umm-maybe/phi-1_5-finetuned-skip0clip", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("umm-maybe/phi-1_5-finetuned-skip0clip", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use umm-maybe/phi-1_5-finetuned-skip0clip with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "umm-maybe/phi-1_5-finetuned-skip0clip"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "umm-maybe/phi-1_5-finetuned-skip0clip",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/umm-maybe/phi-1_5-finetuned-skip0clip

SGLang

How to use umm-maybe/phi-1_5-finetuned-skip0clip 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 "umm-maybe/phi-1_5-finetuned-skip0clip" \
    --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": "umm-maybe/phi-1_5-finetuned-skip0clip",
		"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 "umm-maybe/phi-1_5-finetuned-skip0clip" \
        --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": "umm-maybe/phi-1_5-finetuned-skip0clip",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use umm-maybe/phi-1_5-finetuned-skip0clip with Docker Model Runner:
```
docker model run hf.co/umm-maybe/phi-1_5-finetuned-skip0clip
```

umm-maybe commited on Sep 22, 2023

Commit

6e53ef7

1 Parent(s): 35a5307

Training in progress, epoch 1

Browse files

Files changed (2) hide show

adapter_model.bin +1 -1
training_args.bin +1 -1

adapter_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae74a572b9c00c388e40c32f9c40cebd22f8a00776cc81773d15ec5720d552a1
 size 18907665

 version https://git-lfs.github.com/spec/v1
+oid sha256:f6829b6a5992f4f96a28259c550b88d33358e4a8acca0067c21478152d1abc63
 size 18907665

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4db0ae4a01d15b7cb4f7460371ccd3b965337dbdf5fddcfc4de8d8d7159cd06f
 size 4091

 version https://git-lfs.github.com/spec/v1
+oid sha256:d5d5847bfcaaa004d98bd415b89fd82755b0330036e081a0b8b502e57e0928dc
 size 4091