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
```

Error in Flash Attention

#34

by Sayan01 - opened Nov 22, 2024

Discussion

Sayan01

Nov 22, 2024

•

edited Nov 22, 2024

Hi, I am getting the following error while running backpropagation on it. I updated my codebase based on the suggestion here, but the issue persists. https://huggingface.co/microsoft/Phi-3-small-128k-instruct/commit/ed7de9a074b0760e6cf050fe1d103b90834933c8

new block_sparse_attn op constructed with config: n_heads=32, max_seq_len=131072, sparse_block_size=64, local_blocks=16, vert_stride=8, homo_head=False, active_head_range=None, kwargs={'kernel_block_size': 64, 'inference': True}
Traceback (most recent call last):
File ".../Code/Phi3/Phi3-C4-small-L-Cosine-Masked-All.py", line 257, in
loss_sum.backward()
File "....conda/envs/demo/lib/python3.12/site-packages/torch/_tensor.py", line 522, in backward
torch.autograd.backward(
File ".../.conda/envs/demo/lib/python3.12/site-packages/torch/autograd/init.py", line 266, in backward
Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass
File ".../.conda/envs/demo/lib/python3.12/site-packages/torch/autograd/function.py", line 289, in apply
return user_fn(self, *args)
^^^^^^^^^^^^^^^^^^^^
File ".../huggingface/modules/transformers_modules/microsoft/Phi-3-small-128k-instruct/ad85cab62be398dc90203c4377a4ccbf090fbb36/triton_flash_blocksparse_attn.py", line 906, in backward
return _backward(ctx, do, *backward_layout)[:4]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File ".../huggingface/modules/transformers_modules/microsoft/Phi-3-small-128k-instruct/ad85cab62be398dc90203c4377a4ccbf090fbb36/triton_flash_blocksparse_attn.py", line 683, in _backward
delta = torch.empty_like(l)
^^^^^^^^^^^^^^^^^^^
TypeError: empty_like(): argument 'input' (position 1) must be Tensor, not NoneType

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