Instructions to use microsoft/phi-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/phi-1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="microsoft/phi-1")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-1") model = AutoModelForCausalLM.from_pretrained("microsoft/phi-1") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use microsoft/phi-1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "microsoft/phi-1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "microsoft/phi-1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/microsoft/phi-1
- SGLang
How to use microsoft/phi-1 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-1" \ --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": "microsoft/phi-1", "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 "microsoft/phi-1" \ --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": "microsoft/phi-1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use microsoft/phi-1 with Docker Model Runner:
docker model run hf.co/microsoft/phi-1
fix(root): Fixes relative paths.
Browse files- configuration_phi.py +3 -3
- modeling_phi.py +6 -6
configuration_phi.py
CHANGED
|
@@ -16,8 +16,8 @@
|
|
| 16 |
""" Phi model configuration"""
|
| 17 |
|
| 18 |
|
| 19 |
-
from .
|
| 20 |
-
from .
|
| 21 |
|
| 22 |
|
| 23 |
logger = logging.get_logger(__name__)
|
|
@@ -25,7 +25,7 @@ logger = logging.get_logger(__name__)
|
|
| 25 |
PHI_PRETRAINED_CONFIG_ARCHIVE_MAP = {
|
| 26 |
"microsoft/phi-1": "https://huggingface.co/microsoft/phi-1/resolve/main/config.json",
|
| 27 |
"microsoft/phi-1_5": "https://huggingface.co/microsoft/phi-1_5/resolve/main/config.json",
|
| 28 |
-
"microsoft/phi-2": "https://huggingface.co/microsoft/phi-
|
| 29 |
}
|
| 30 |
|
| 31 |
|
|
|
|
| 16 |
""" Phi model configuration"""
|
| 17 |
|
| 18 |
|
| 19 |
+
from transformers.configuration_utils import PretrainedConfig
|
| 20 |
+
from transformers.utils import logging
|
| 21 |
|
| 22 |
|
| 23 |
logger = logging.get_logger(__name__)
|
|
|
|
| 25 |
PHI_PRETRAINED_CONFIG_ARCHIVE_MAP = {
|
| 26 |
"microsoft/phi-1": "https://huggingface.co/microsoft/phi-1/resolve/main/config.json",
|
| 27 |
"microsoft/phi-1_5": "https://huggingface.co/microsoft/phi-1_5/resolve/main/config.json",
|
| 28 |
+
"microsoft/phi-2": "https://huggingface.co/microsoft/phi-2/resolve/main/config.json",
|
| 29 |
}
|
| 30 |
|
| 31 |
|
modeling_phi.py
CHANGED
|
@@ -25,17 +25,17 @@ import torch.utils.checkpoint
|
|
| 25 |
from torch import nn
|
| 26 |
from torch.nn import BCEWithLogitsLoss, CrossEntropyLoss, MSELoss
|
| 27 |
|
| 28 |
-
from .
|
| 29 |
-
from .
|
| 30 |
-
from .
|
| 31 |
-
from .
|
| 32 |
BaseModelOutputWithPast,
|
| 33 |
CausalLMOutputWithPast,
|
| 34 |
SequenceClassifierOutputWithPast,
|
| 35 |
TokenClassifierOutput,
|
| 36 |
)
|
| 37 |
-
from .
|
| 38 |
-
from .
|
| 39 |
add_code_sample_docstrings,
|
| 40 |
add_start_docstrings,
|
| 41 |
add_start_docstrings_to_model_forward,
|
|
|
|
| 25 |
from torch import nn
|
| 26 |
from torch.nn import BCEWithLogitsLoss, CrossEntropyLoss, MSELoss
|
| 27 |
|
| 28 |
+
from transformers.activations import ACT2FN
|
| 29 |
+
from transformers.cache_utils import Cache, DynamicCache
|
| 30 |
+
from transformers.modeling_attn_mask_utils import _prepare_4d_causal_attention_mask
|
| 31 |
+
from transformers.modeling_outputs import (
|
| 32 |
BaseModelOutputWithPast,
|
| 33 |
CausalLMOutputWithPast,
|
| 34 |
SequenceClassifierOutputWithPast,
|
| 35 |
TokenClassifierOutput,
|
| 36 |
)
|
| 37 |
+
from transformers.modeling_utils import PreTrainedModel
|
| 38 |
+
from transformers.utils import (
|
| 39 |
add_code_sample_docstrings,
|
| 40 |
add_start_docstrings,
|
| 41 |
add_start_docstrings_to_model_forward,
|