Instructions to use snoop2head/kogpt-conditional-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use snoop2head/kogpt-conditional-2 with Transformers:

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

pipe = pipeline("text-generation", model="snoop2head/kogpt-conditional-2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("snoop2head/kogpt-conditional-2")
model = AutoModelForCausalLM.from_pretrained("snoop2head/kogpt-conditional-2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use snoop2head/kogpt-conditional-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "snoop2head/kogpt-conditional-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "snoop2head/kogpt-conditional-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/snoop2head/kogpt-conditional-2

SGLang

How to use snoop2head/kogpt-conditional-2 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 "snoop2head/kogpt-conditional-2" \
    --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": "snoop2head/kogpt-conditional-2",
		"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 "snoop2head/kogpt-conditional-2" \
        --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": "snoop2head/kogpt-conditional-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use snoop2head/kogpt-conditional-2 with Docker Model Runner:
```
docker model run hf.co/snoop2head/kogpt-conditional-2
```

snoop2head commited on Dec 25, 2021

Commit

2829646

1 Parent(s): 50a11fc

Upload tokenizer_config.json

Browse files

Files changed (1) hide show

tokenizer_config.json +1 -0

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1 @@

+ {"max_len": 42, "padding": "max_length", "add_special_tokens": true, "return_tensors": "pt", "truncation": true, "bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": "/opt/ml/.cache/huggingface/transformers/c2ab65b9d700d0871fd407d489869d7b93f69fb5f1a58fb1fac796fd43b9ea27.1f5b09bb43973b9fbd2ba75c9fe44ffab036b980c4e6a9d779aa7707913416fe", "name_or_path": "skt/ko-gpt-trinity-1.2B-v0.5", "tokenizer_class": "PreTrainedTokenizerFast"}