Instructions to use makemecker/finetune_results with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use makemecker/finetune_results with Transformers:

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

pipe = pipeline("image-text-to-text", model="makemecker/finetune_results")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("makemecker/finetune_results")
model = AutoModelForMultimodalLM.from_pretrained("makemecker/finetune_results", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use makemecker/finetune_results with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/makemecker/finetune_results

SGLang

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

Docker Model Runner
How to use makemecker/finetune_results with Docker Model Runner:
```
docker model run hf.co/makemecker/finetune_results
```

makemecker commited on Jun 12, 2024

Commit

7643cbd

verified ·

1 Parent(s): ebf0b47

Training in progress, step 5000

Browse files

Files changed (1) hide show

runs/Jun12_11-41-10_901a0e2dd361/events.out.tfevents.1718192471.901a0e2dd361.901613.0 +2 -2

runs/Jun12_11-41-10_901a0e2dd361/events.out.tfevents.1718192471.901a0e2dd361.901613.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e466b91af9830b84368aed0674fb0a8eb11b2ef88b13a5d1369425cdade4b5a
-size 13585

 version https://git-lfs.github.com/spec/v1
+oid sha256:feb3d966ad8e91599f8ac78a11c31ddae1950ac69df6380708fca8c847381039
+size 15695