Instructions to use ParScale/ParScale-1.8B-P1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ParScale/ParScale-1.8B-P1 with Transformers:

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

pipe = pipeline("text-generation", model="ParScale/ParScale-1.8B-P1", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("ParScale/ParScale-1.8B-P1", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ParScale/ParScale-1.8B-P1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ParScale/ParScale-1.8B-P1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ParScale/ParScale-1.8B-P1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ParScale/ParScale-1.8B-P1

SGLang

How to use ParScale/ParScale-1.8B-P1 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 "ParScale/ParScale-1.8B-P1" \
    --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": "ParScale/ParScale-1.8B-P1",
		"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 "ParScale/ParScale-1.8B-P1" \
        --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": "ParScale/ParScale-1.8B-P1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ParScale/ParScale-1.8B-P1 with Docker Model Runner:
```
docker model run hf.co/ParScale/ParScale-1.8B-P1
```

chenmouxiang commited on May 17, 2025

Commit

79ae419

verified ·

1 Parent(s): 0ef0043

Update README.md

Browse files

Files changed (1) hide show

README.md +10 -1

README.md CHANGED Viewed

@@ -1,3 +1,12 @@
 <div align="center">
@@ -77,4 +86,4 @@ Download link: https://huggingface.co/ParScale/ParScale-{size}-{P}-{dataset}
 - {size}: model size, from {0.7B, 0.9B, 1.3B, 1.8B, 3B, 4.7B}
 - {P}: number of parallels, from {P1, P2, P4, P8}
-- {dataset}: training dataset, from {Python, Pile}

+---
+datasets:
+- HuggingFaceFW/fineweb-edu
+- HuggingFaceTB/cosmopedia
+- HuggingFaceTB/finemath
+- bigcode/the-stack-v2
+- HuggingFaceTB/stack-edu
+license: apache-2.0
+---
 <div align="center">
 - {size}: model size, from {0.7B, 0.9B, 1.3B, 1.8B, 3B, 4.7B}
 - {P}: number of parallels, from {P1, P2, P4, P8}
+- {dataset}: training dataset, from {Python, Pile}