Instructions to use microsoft/Phi-3-small-128k-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use microsoft/Phi-3-small-128k-instruct with Transformers:

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

pipe = pipeline("text-generation", model="microsoft/Phi-3-small-128k-instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-3-small-128k-instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use microsoft/Phi-3-small-128k-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "microsoft/Phi-3-small-128k-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/Phi-3-small-128k-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/microsoft/Phi-3-small-128k-instruct

SGLang

How to use microsoft/Phi-3-small-128k-instruct 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 "microsoft/Phi-3-small-128k-instruct" \
    --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": "microsoft/Phi-3-small-128k-instruct",
		"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 "microsoft/Phi-3-small-128k-instruct" \
        --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": "microsoft/Phi-3-small-128k-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use microsoft/Phi-3-small-128k-instruct with Docker Model Runner:
```
docker model run hf.co/microsoft/Phi-3-small-128k-instruct
```

CheckpointError in `triton_flash_blocksparse_attn.py` while finetuning

#18

by FremyCompany - opened Jun 16, 2024

Discussion

FremyCompany

Jun 16, 2024

While trying to finetune this model, I encountered an error with the backward pass:

  File "/root/.cache/huggingface/modules/transformers_modules/microsoft/Phi-3-small-128k-instruct/f80aaa30bfc64c2b8ab214b541d9050e97163bc4/triton_flash_blocksparse_attn.py", line 904, in backward
    return _backward(ctx, do, *backward_layout)[:4]
  File "/root/.cache/huggingface/modules/transformers_modules/microsoft/Phi-3-small-128k-instruct/f80aaa30bfc64c2b8ab214b541d9050e97163bc4/triton_flash_blocksparse_attn.py", line 655, in _backward
    q, k, v, o, l, m, layout_crow_indices, layout_col_indices = ctx.saved_tensors
  File "/usr/local/lib/python3.10/dist-packages/torch/utils/checkpoint.py", line 1118, in unpack_hook
    raise CheckpointError(
torch.utils.checkpoint.CheckpointError: torch.utils.checkpoint: Unpack is being triggered for a tensor that was already unpacked once. If you are calling ctx.saved_tensors in backward, make sure to do so only once. Otherwise please open an issue with details on your use case.

Any idea how I could fix this issue?

FremyCompany

Jun 16, 2024

Nevermind, after looking deeper into the other issues in the Phi3 repositories, I was able to locate that the error is related to the use of use_reentrant=False in the Trainer configuration, while use_reentrant=True is apparently required for Phi3 small.

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