Instructions to use atsumoto/phi-2-alpaca-cleaned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use atsumoto/phi-2-alpaca-cleaned with Transformers:

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

pipe = pipeline("text-generation", model="atsumoto/phi-2-alpaca-cleaned", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("atsumoto/phi-2-alpaca-cleaned", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("atsumoto/phi-2-alpaca-cleaned", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use atsumoto/phi-2-alpaca-cleaned with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/atsumoto/phi-2-alpaca-cleaned

SGLang

How to use atsumoto/phi-2-alpaca-cleaned 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 "atsumoto/phi-2-alpaca-cleaned" \
    --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": "atsumoto/phi-2-alpaca-cleaned",
		"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 "atsumoto/phi-2-alpaca-cleaned" \
        --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": "atsumoto/phi-2-alpaca-cleaned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use atsumoto/phi-2-alpaca-cleaned with Docker Model Runner:
```
docker model run hf.co/atsumoto/phi-2-alpaca-cleaned
```

phi-2-alpaca-cleaned / README.md

Atsumoto Ohashi

Update README.md

afc4c53 verified over 2 years ago

preview code

Raw

History Blame Contribute Delete

1.2 kB

metadata

license: mit
datasets:
  - yahma/alpaca-cleaned
language:
  - en
library_name: transformers
pipeline_tag: text-generation

phi-2-alpaca-cleaned

This model is an instruction-tuned version of the microsoft/phi-2 model fine-tuned on the yahma/alpaca-cleaned dataset.

In the training, full parameter fine-tuning of phi-2 was performed, and LoRA was not used.

Text Format

Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
Based on the information provided, rewrite the sentence by changing its tense from past to future.

### Input:
She played the piano beautifully for hours and then stopped as it was midnight.	

### Response:
She will play the piano beautifully for hours and then stop as it will be midnight.

Training

GPUs: 8 × A6000 48GB
per_device_train_batch_size: 8
gradient_accumulation_steps: 8
per_device_eval_batch_size: 8
num_train_epochs: 3
learning_rate: 2e-5
warmup_ratio: 0.03

Software

pytorch: 2.1.2
transformers: 4.38.0.dev0
accelerate: 0.26.1
deepspeed: 0.13.1