Instructions to use Tverous/sft-trl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tverous/sft-trl with Transformers:

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

pipe = pipeline("text-generation", model="Tverous/sft-trl")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Tverous/sft-trl")
model = AutoModelForCausalLM.from_pretrained("Tverous/sft-trl")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Tverous/sft-trl with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Tverous/sft-trl

SGLang

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

Docker Model Runner
How to use Tverous/sft-trl with Docker Model Runner:
```
docker model run hf.co/Tverous/sft-trl
```

sft-trl

Commit History

update model card README.md

816a89d

Simon Tang commited on Jul 23, 2023

Tverous/sft-trl

bbed8e6

Simon Tang commited on Jul 23, 2023

Training in progress, step 1000

3a2f91f

Simon Tang commited on Jul 22, 2023

initial commit

4548b7d

Simon Tang commited on Jul 22, 2023

Commit History

update model card README.md 816a89d

Tverous/sft-trl bbed8e6

Training in progress, step 1000 3a2f91f

initial commit 4548b7d

update model card README.md

816a89d

Tverous/sft-trl

bbed8e6

Training in progress, step 1000

3a2f91f

initial commit

4548b7d