Instructions to use Manhph2211/PulseLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Manhph2211/PulseLM with Transformers:

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

pipe = pipeline("text-generation", model="Manhph2211/PulseLM", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Manhph2211/PulseLM", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Manhph2211/PulseLM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Manhph2211/PulseLM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Manhph2211/PulseLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Manhph2211/PulseLM

SGLang

How to use Manhph2211/PulseLM 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 "Manhph2211/PulseLM" \
    --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": "Manhph2211/PulseLM",
		"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 "Manhph2211/PulseLM" \
        --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": "Manhph2211/PulseLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Manhph2211/PulseLM with Docker Model Runner:
```
docker model run hf.co/Manhph2211/PulseLM
```

PulseLM / README.md

Manhph2211

1c10b2e 5 days ago

preview code

raw

history blame contribute delete

2.01 kB

metadata

library_name: transformers
language:
  - en
tags:
  - ppg
  - multimodal
  - health
  - qwen
  - physiology
  - biosignal
pipeline_tag: text-generation
base_model: Qwen/Qwen2.5-7B-Instruct
datasets:
  - Manhph2211/PulseLM

PulseLM: A Foundation Dataset and Benchmark for PPG-Text Learning

Quick Start

# transformers>=4.46.0 accelerate>=1.0.1 peft>=0.13.2 safetensors
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

tokenizer = AutoTokenizer.from_pretrained("Manhph2211/PulseLM", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    "Manhph2211/PulseLM",
    trust_remote_code=True,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)