Instructions to use MentaCapture/p4modelasr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MentaCapture/p4modelasr with Transformers:

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

pipe = pipeline("text-generation", model="MentaCapture/p4modelasr", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("MentaCapture/p4modelasr", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MentaCapture/p4modelasr with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MentaCapture/p4modelasr"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MentaCapture/p4modelasr",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MentaCapture/p4modelasr

SGLang

How to use MentaCapture/p4modelasr 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 "MentaCapture/p4modelasr" \
    --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": "MentaCapture/p4modelasr",
		"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 "MentaCapture/p4modelasr" \
        --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": "MentaCapture/p4modelasr",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MentaCapture/p4modelasr with Docker Model Runner:
```
docker model run hf.co/MentaCapture/p4modelasr
```

SKNahin commited on May 5, 2025

Commit

c3c9ad7

verified ·

1 Parent(s): 67f6cd1

Upload Phi4MMForCausalLM

Browse files

Files changed (4) hide show

config.json +1 -1
model-00001-of-00003.safetensors +1 -1
model-00002-of-00003.safetensors +1 -1
model-00003-of-00003.safetensors +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/home/azureuser/phi4/phi4-works/phi4-mini/output_bn_6/checkpoint-8000",
   "architectures": [
     "Phi4MMForCausalLM"
   ],

 {
+  "_name_or_path": "/home/azureuser/phi4/phi4-works/phi4-mini/output_bn_new-13/checkpoint-4000",
   "architectures": [
     "Phi4MMForCausalLM"
   ],

model-00001-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9d707535ea5796cf761f60b5b79213215703b4aea5af4251339172ed3e132ba
 size 4998420448

 version https://git-lfs.github.com/spec/v1
+oid sha256:cb294458f7c7e31e0424b2cbe03df76d7e1f11ab6d5c61d4e016f56302227c96
 size 4998420448

model-00002-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea3ac4b5174e08b42cd54a83100b5532aee2f093543ce7aded98650ad05217fa
 size 4983891952

 version https://git-lfs.github.com/spec/v1
+oid sha256:9cd5b2ee4e041d245b32d3cbfde31ae45292ccd52191e66fd195deb679d81461
 size 4983891952

model-00003-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77dba120141a996657045d95cef8b4a8843eaf3c6872226c7509f3326fa08a41
 size 1905111704

 version https://git-lfs.github.com/spec/v1
+oid sha256:27cbf5326049701392fbbc9b756c882d9c57c54ccd230ae5ab9c7629a090bc30
 size 1905111704