Instructions to use zaenalium/CodeGen-Indo-350M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zaenalium/CodeGen-Indo-350M with Transformers:

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

pipe = pipeline("text-generation", model="zaenalium/CodeGen-Indo-350M")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zaenalium/CodeGen-Indo-350M")
model = AutoModelForCausalLM.from_pretrained("zaenalium/CodeGen-Indo-350M", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use zaenalium/CodeGen-Indo-350M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zaenalium/CodeGen-Indo-350M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zaenalium/CodeGen-Indo-350M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/zaenalium/CodeGen-Indo-350M

SGLang

How to use zaenalium/CodeGen-Indo-350M 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 "zaenalium/CodeGen-Indo-350M" \
    --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": "zaenalium/CodeGen-Indo-350M",
		"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 "zaenalium/CodeGen-Indo-350M" \
        --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": "zaenalium/CodeGen-Indo-350M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use zaenalium/CodeGen-Indo-350M with Docker Model Runner:
```
docker model run hf.co/zaenalium/CodeGen-Indo-350M
```

zaenalium commited on Feb 1, 2024

Commit

f1062bb

verified ·

1 Parent(s): 9dc0b28

Training in progress, step 8000

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/Jan31_15-19-38_9e34846f7a4e/events.out.tfevents.1706715485.9e34846f7a4e.26.0 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69ceb3b97dd665191c8e2acf7efac429e783317a1dc6f3739b42b74ce68af514
 size 1426867192

 version https://git-lfs.github.com/spec/v1
+oid sha256:250640e3a348c5b05f71ca40e1f42e9ddbebab25bc58214c364826940efb4a32
 size 1426867192

runs/Jan31_15-19-38_9e34846f7a4e/events.out.tfevents.1706715485.9e34846f7a4e.26.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3120d355c1d43cc08138e9e0051d25995cb4d081cfa72e49f383d5a766ca7c57
-size 9420

 version https://git-lfs.github.com/spec/v1
+oid sha256:21476bf128f4c829bfc572a9bd377a80d52a29cec8d06be0c71fcba06e35c587
+size 10990