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

Libraries

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

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

pipe = pipeline("text-generation", model="microsoft/Phi-3-vision-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-vision-128k-instruct", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

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

Fix generation when `repetition_penalty` is activated

#57

by YenChunChen - opened Aug 2, 2024

base: refs/heads/main

←

from: refs/pr/57

Discussion Files changed

+10

-1

Files changed (1) hide show

image_embedding_phi3_v.py +10 -1

image_embedding_phi3_v.py CHANGED Viewed

@@ -12,6 +12,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
 import torch
 from torch import nn
@@ -191,7 +192,15 @@ class Phi3ImageEmbedding(nn.Module):
         # positions for image tokens
         positions = torch.nonzero((input_ids < 0) & (input_ids > -MAX_INPUT_ID), as_tuple=True)
         has_image = len(positions[0].tolist()) > 0
-        input_ids = input_ids.clamp_min(0).clamp_max(self.vocab_size).detach()
         hidden_states = self.wte(input_ids)
         if has_image:

 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+import warnings
 import torch
 from torch import nn
         # positions for image tokens
         positions = torch.nonzero((input_ids < 0) & (input_ids > -MAX_INPUT_ID), as_tuple=True)
         has_image = len(positions[0].tolist()) > 0
+        # input_ids = input_ids.clamp_min(0).clamp_max(self.vocab_size).detach()
+        input_ids.clamp_min_(0).clamp_max_(self.vocab_size)
+        warnings.warn(
+            "Phi-3-V modifies `input_ids` in-place and the tokens indicating images will be "
+            "removed after model forward. If your workflow requires multiple forward passes on "
+            "the same `input_ids`, please make a copy of `input_ids` before passing it to the "
+            "model."
+        )
         hidden_states = self.wte(input_ids)
         if has_image: