Instructions to use prismdata/Perdix-1.1B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prismdata/Perdix-1.1B-Base with Transformers:

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

pipe = pipeline("text-generation", model="prismdata/Perdix-1.1B-Base", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("prismdata/Perdix-1.1B-Base", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use prismdata/Perdix-1.1B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prismdata/Perdix-1.1B-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prismdata/Perdix-1.1B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/prismdata/Perdix-1.1B-Base

SGLang

How to use prismdata/Perdix-1.1B-Base 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 "prismdata/Perdix-1.1B-Base" \
    --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": "prismdata/Perdix-1.1B-Base",
		"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 "prismdata/Perdix-1.1B-Base" \
        --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": "prismdata/Perdix-1.1B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use prismdata/Perdix-1.1B-Base with Docker Model Runner:
```
docker model run hf.co/prismdata/Perdix-1.1B-Base
```

prismdata commited on 5 days ago

Commit

df10b8f

verified ·

1 Parent(s): 559cf86

모델 카드에 학습 데이터 저장소(Perdix-Pretrain-Data) 링크 추가

Browse files

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -11,6 +11,7 @@ tags:
 - differential-attention
 - polynorm
 datasets:
 - mlfoundations/dclm-baseline-1.0
 - HuggingFaceFW/fineweb-2
 - HuggingFaceTB/finemath
@@ -82,6 +83,7 @@ print(tok.decode(out[0], skip_special_tokens=True))
 ## 학습
 - **데이터**: 30B 토큰. 영어 웹([DCLM-baseline](https://huggingface.co/datasets/mlfoundations/dclm-baseline-1.0), CC-BY-4.0), 한국어 웹([FineWeb2](https://huggingface.co/datasets/HuggingFaceFW/fineweb-2) kor_Hang, ODC-By), 수학([FineMath](https://huggingface.co/datasets/HuggingFaceTB/finemath) 4+, ODC-By)
 - **믹싱**: 영어 65% / 한국어 30% / 수학 5%에서 시작해 25% / 50% / 25%로 서서히 바꿨습니다.
 - **학습률**: 최고 3e-4. 1B 토큰 워밍업 뒤 유지하다 마지막 20% 구간에서 최고값의 25%까지 내렸습니다.
 - **배치**: 스텝당 약 1M 토큰, 시퀀스 길이 2,048, bf16

 - differential-attention
 - polynorm
 datasets:
+- prismdata/Perdix-Pretrain-Data
 - mlfoundations/dclm-baseline-1.0
 - HuggingFaceFW/fineweb-2
 - HuggingFaceTB/finemath
 ## 학습
 - **데이터**: 30B 토큰. 영어 웹([DCLM-baseline](https://huggingface.co/datasets/mlfoundations/dclm-baseline-1.0), CC-BY-4.0), 한국어 웹([FineWeb2](https://huggingface.co/datasets/HuggingFaceFW/fineweb-2) kor_Hang, ODC-By), 수학([FineMath](https://huggingface.co/datasets/HuggingFaceTB/finemath) 4+, ODC-By)
+  - 실제로 쓴 parquet 파일(335개, 178GB)은 [prismdata/Perdix-Pretrain-Data](https://huggingface.co/datasets/prismdata/Perdix-Pretrain-Data)에 그대로 올려 두었습니다.
 - **믹싱**: 영어 65% / 한국어 30% / 수학 5%에서 시작해 25% / 50% / 25%로 서서히 바꿨습니다.
 - **학습률**: 최고 3e-4. 1B 토큰 워밍업 뒤 유지하다 마지막 20% 구간에서 최고값의 25%까지 내렸습니다.
 - **배치**: 스텝당 약 1M 토큰, 시퀀스 길이 2,048, bf16