Instructions to use daekeun-ml/phi-2-ko-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use daekeun-ml/phi-2-ko-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="daekeun-ml/phi-2-ko-v0.1", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("daekeun-ml/phi-2-ko-v0.1", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("daekeun-ml/phi-2-ko-v0.1", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use daekeun-ml/phi-2-ko-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "daekeun-ml/phi-2-ko-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "daekeun-ml/phi-2-ko-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/daekeun-ml/phi-2-ko-v0.1

SGLang

How to use daekeun-ml/phi-2-ko-v0.1 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 "daekeun-ml/phi-2-ko-v0.1" \
    --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": "daekeun-ml/phi-2-ko-v0.1",
		"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 "daekeun-ml/phi-2-ko-v0.1" \
        --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": "daekeun-ml/phi-2-ko-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use daekeun-ml/phi-2-ko-v0.1 with Docker Model Runner:
```
docker model run hf.co/daekeun-ml/phi-2-ko-v0.1
```

Encoding of vocabulary

by SDFASDGA - opened Feb 10, 2024

Discussion

SDFASDGA

Feb 10, 2024

Can you please tell me what is the encoding of the vocabulary text? For example, the readme example shows tokenizer output of ['ìķĦë§Ī', 'ì¡´', 'ĠìĦ¸', 'ìĿ´ì§Ģ', 'ë©ĶìĿ´', 'ì»¤'] when tokenizing "아마존 세이지메이커". How do I map the tokens to the korean characters unicode characters?

daekeun-ml

Owner Feb 12, 2024

•

edited Feb 12, 2024

The tokenizer used in phi-2 is not a BPE, but a byte-level BPE like GPT-2, so Unicode conversion is required to check normal characters.

See Colab below for more details.
https://colab.research.google.com/drive/15tMASZ0NLm8bnxkM4uXCRgdzznSpbp9L?usp=sharing#scrollTo=UwJT5ZSfwOGc

See the code snippet below to restore the original string.

input_str = "아마존 세이지메이커"
tokenized = tokenizer.tokenize(input_str)
encoded = tokenizer.encode_plus(input_str)
decoded = tokenizer.decode(encoded['input_ids'])
print(encoded)
print(tokenized) # just mapping to token id; you cannot see the actual character!
print(decoded)

daekeun-ml changed discussion status to closed Feb 12, 2024

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment