Instructions to use binga/style-mimic-pilot-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use binga/style-mimic-pilot-tiny with Transformers:

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

pipe = pipeline("text-generation", model="binga/style-mimic-pilot-tiny")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("binga/style-mimic-pilot-tiny")
model = AutoModelForCausalLM.from_pretrained("binga/style-mimic-pilot-tiny")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use binga/style-mimic-pilot-tiny with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/binga/style-mimic-pilot-tiny

SGLang

How to use binga/style-mimic-pilot-tiny 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 "binga/style-mimic-pilot-tiny" \
    --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": "binga/style-mimic-pilot-tiny",
		"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 "binga/style-mimic-pilot-tiny" \
        --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": "binga/style-mimic-pilot-tiny",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use binga/style-mimic-pilot-tiny with Docker Model Runner:
```
docker model run hf.co/binga/style-mimic-pilot-tiny
```

binga commited on 30 days ago

Commit

33134e9

verified ·

1 Parent(s): 325796b

Pilot data pipeline smoke test

Browse files

Files changed (1) hide show

README.md +2 -3

README.md CHANGED Viewed

@@ -4,10 +4,9 @@ library_name: transformers
 model_name: style-mimic-pilot-tiny
 tags:
 - generated_from_trainer
-- trackio:https://binga-mlintern-style26.hf.space?project=style-mimic&runs=pilot-data-tiny-gpt2&sidebar=collapsed
 - hf_jobs
-- trl
 - sft
 licence: license
 ---
@@ -30,7 +29,7 @@ print(output["generated_text"])
 ## Training procedure
-[<img src="https://raw.githubusercontent.com/gradio-app/trackio/refs/heads/main/trackio/assets/badge.png" alt="Visualize in Trackio" title="Visualize in Trackio" width="150" height="24"/>](https://binga-mlintern-style26.hf.space?project=style-mimic&runs=pilot-data-tiny-gpt2&sidebar=collapsed)
 This model was trained with SFT.

 model_name: style-mimic-pilot-tiny
 tags:
 - generated_from_trainer
 - hf_jobs
 - sft
+- trl
 licence: license
 ---
 ## Training procedure
 This model was trained with SFT.