Instructions to use HenryJJ/Instruct_Phi2_Dolly15K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HenryJJ/Instruct_Phi2_Dolly15K with Transformers:

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

pipe = pipeline("text-generation", model="HenryJJ/Instruct_Phi2_Dolly15K", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("HenryJJ/Instruct_Phi2_Dolly15K", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use HenryJJ/Instruct_Phi2_Dolly15K with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HenryJJ/Instruct_Phi2_Dolly15K"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HenryJJ/Instruct_Phi2_Dolly15K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HenryJJ/Instruct_Phi2_Dolly15K

SGLang

How to use HenryJJ/Instruct_Phi2_Dolly15K 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 "HenryJJ/Instruct_Phi2_Dolly15K" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HenryJJ/Instruct_Phi2_Dolly15K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "HenryJJ/Instruct_Phi2_Dolly15K" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HenryJJ/Instruct_Phi2_Dolly15K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HenryJJ/Instruct_Phi2_Dolly15K with Docker Model Runner:
```
docker model run hf.co/HenryJJ/Instruct_Phi2_Dolly15K
```

Instruct_Phi2_Dolly15K

Fine-tuned from phi2，used Dolly15k for the dataset. 90% for training, 10% validation. Trained for 2.0 epochs using QLora. Trained with 1024 context window.

Model Details

Trained by: trained by HenryJJ.
Model type: Instruct_Phi2_Dolly15K is an auto-regressive language model based on the phi 2 transformer architecture.
Language(s): English
License for HenryJJ/Instruct_Phi2_Dolly15K: apache-2.0 license

Prompting

Prompt Template With Context

chatml format

<|im_start|>system
{instruction}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Prompt Template Without Context

<|im_start|>system
{instruction}<|im_end|>
<|im_start|>assistant

Training script:

Fully opensourced at: https://github.com/hengjiUSTC/learn-llm/blob/main/trl_finetune.py. Run on 1 A10G instance for 4 hours.

python3 trl_finetune.py --config configs/phi2-dolly.yml

Downloads last month: 7

Safetensors

Model size

3B params

Tensor type

BF16

HenryJJ
/

Instruct_Phi2_Dolly15K