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

Libraries

How to use indobenchmark/indogpt with Transformers:

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

pipe = pipeline("text-generation", model="indobenchmark/indogpt")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("indobenchmark/indogpt")
model = AutoModelForCausalLM.from_pretrained("indobenchmark/indogpt", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use indobenchmark/indogpt with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/indobenchmark/indogpt

SGLang

How to use indobenchmark/indogpt 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 "indobenchmark/indogpt" \
    --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": "indobenchmark/indogpt",
		"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 "indobenchmark/indogpt" \
        --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": "indobenchmark/indogpt",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

Samuel Cahyawijaya commited on Sep 27, 2021

Commit

cdb45df

1 Parent(s): f810cd7

update model & tokenizer meta

Browse files

Files changed (3) hide show

config.json +1 -1
special_tokens_map.json +1 -1
tokenizer_config.json +1 -1

config.json CHANGED Viewed

@@ -28,5 +28,5 @@
     }
   },
   "tokenizer_class": "IndoNLGTokenizer",
-  "vocab_size": 40005
 }

     }
   },
   "tokenizer_class": "IndoNLGTokenizer",
+  "vocab_size": 40006
 }

special_tokens_map.json CHANGED Viewed

	@@ -1 +1 @@
1	- {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, "additional_special_tokens": ["[java]", "[sunda]", "[~~indo~~]", "<mask>"]}


1	+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, "additional_special_tokens": ["[java]", "[sunda]", "[indonesia]", "<mask>", "[english]"]}

tokenizer_config.json CHANGED Viewed

	@@ -1 +1 @@
1	- {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "additional_special_tokens": ["[java]", "[sunda]", "[~~indo~~]", "<mask>"]}


1	+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "additional_special_tokens": ["[java]", "[sunda]", "[indonesia]", "<mask>", "[english]"]}