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
```

"OutOfResources: out of resource: shared memory, Required: 180224, Hardware limit: 101376. "

#27

by joker26 - opened Jul 21, 2024

Discussion

joker26

Jul 21, 2024

I'm getting the following error when running the model, here are the details as follow：
“Traceback (most recent call last):
File "/hy-tmp/RAG/app/test_RAG.py", line 154, in
main()
File "/hy-tmp/RAG/app/test_RAG.py", line 123, in main
answer = llm.predict('\n'.join(rerank_res), query).strip()
File "/hy-tmp/RAG/app/llm_infer.py", line 284, in predict
response = self.phi_infer_test(context)
File "/hy-tmp/RAG/app/llm_infer.py", line 229, in phi_infer_test
generated_ids = self.model.generate(
File "/usr/local/miniconda3/envs/myconda/lib/python3.9/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/usr/local/miniconda3/envs/myconda/lib/python3.9/site-packages/transformers/generation/utils.py", line 1969, in generate
result = self._sample(
File "/usr/local/miniconda3/envs/myconda/lib/python3.9/site-packages/transformers/generation/utils.py", line 2912, in _sample
outputs = self(**model_inputs, return_dict=True)
File "/usr/local/miniconda3/envs/myconda/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/usr/local/miniconda3/envs/myconda/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "/root/.cache/huggingface/modules/transformers_modules/Phi-3-small-128k-instruct/modeling_phi3_small.py", line 956, in forward
outputs = self.model(
File "/usr/local/miniconda3/envs/myconda/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/usr/local/miniconda3/envs/myconda/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "/root/.cache/huggingface/modules/transformers_modules/Phi-3-small-128k-instruct/modeling_phi3_small.py", line 859, in forward
layer_outputs = decoder_layer(
File "/usr/local/miniconda3/envs/myconda/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/usr/local/miniconda3/envs/myconda/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "/root/.cache/huggingface/modules/transformers_modules/Phi-3-small-128k-instruct/modeling_phi3_small.py", line 671, in forward
hidden_states, self_attn_weights, present_key_values = self.self_attn(
File "/usr/local/miniconda3/envs/myconda/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/usr/local/miniconda3/envs/myconda/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "/root/.cache/huggingface/modules/transformers_modules/Phi-3-small-128k-instruct/modeling_phi3_small.py", line 616, in forward
attn_function_output = self._apply_blocksparse_attention(
File "/root/.cache/huggingface/modules/transformers_modules/Phi-3-small-128k-instruct/modeling_phi3_small.py", line 382, in _apply_blocksparse_attention
context_layer = self._blocksparse_layer(
File "/usr/local/miniconda3/envs/myconda/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/usr/local/miniconda3/envs/myconda/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "/root/.cache/huggingface/modules/transformers_modules/Phi-3-small-128k-instruct/triton_blocksparse_attention_layer.py", line 165, in forward
return blocksparse_flash_attn_padded_fwd(
File "/root/.cache/huggingface/modules/transformers_modules/Phi-3-small-128k-instruct/triton_flash_blocksparse_attn.py", line 994, in blocksparse_flash_attn_padded_fwd
_fwd_kernel_batch_inference[grid](
File "/usr/local/miniconda3/envs/myconda/lib/python3.9/site-packages/triton/runtime/jit.py", line 167, in
return lambda *args, **kwargs: self.run(grid=grid, warmup=False, *args, **kwargs)
File "/usr/local/miniconda3/envs/myconda/lib/python3.9/site-packages/triton/runtime/autotuner.py", line 305, in run
return self.fn.run(*args, **kwargs)
File "/usr/local/miniconda3/envs/myconda/lib/python3.9/site-packages/triton/runtime/jit.py", line 425, in run
kernel.run(grid_0, grid_1, grid_2, kernel.num_warps, kernel.num_ctas, # number of warps/ctas per instance
File "/usr/local/miniconda3/envs/myconda/lib/python3.9/site-packages/triton/compiler/compiler.py", line 255, in getattribute
self._init_handles()
File "/usr/local/miniconda3/envs/myconda/lib/python3.9/site-packages/triton/compiler/compiler.py", line 248, in _init_handles
raise OutOfResources(self.shared, max_shared, "shared memory")
triton.runtime.autotuner.OutOfResources: out of resource: shared memory, Required: 180224, Hardware limit: 101376. Reducing block sizes or num_stages may help.”

joker26

Jul 21, 2024

I'm having this problem with my 4090 and 3090.

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