Instructions to use AksaraLLM/aksarallm-1.5b-v2-checkpoint with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AksaraLLM/aksarallm-1.5b-v2-checkpoint with Transformers:

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

pipe = pipeline("text-generation", model="AksaraLLM/aksarallm-1.5b-v2-checkpoint")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AksaraLLM/aksarallm-1.5b-v2-checkpoint")
model = AutoModelForCausalLM.from_pretrained("AksaraLLM/aksarallm-1.5b-v2-checkpoint", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AksaraLLM/aksarallm-1.5b-v2-checkpoint with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AksaraLLM/aksarallm-1.5b-v2-checkpoint"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AksaraLLM/aksarallm-1.5b-v2-checkpoint",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AksaraLLM/aksarallm-1.5b-v2-checkpoint

SGLang

How to use AksaraLLM/aksarallm-1.5b-v2-checkpoint 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 "AksaraLLM/aksarallm-1.5b-v2-checkpoint" \
    --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": "AksaraLLM/aksarallm-1.5b-v2-checkpoint",
		"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 "AksaraLLM/aksarallm-1.5b-v2-checkpoint" \
        --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": "AksaraLLM/aksarallm-1.5b-v2-checkpoint",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AksaraLLM/aksarallm-1.5b-v2-checkpoint with Docker Model Runner:
```
docker model run hf.co/AksaraLLM/aksarallm-1.5b-v2-checkpoint
```

aksarallm-1.5b-v2-checkpoint

Earlier 1.5B Qwen2-based Indonesian checkpoint. Superseded by AksaraLLM/AksaraLLM-Qwen-1.5B-v5-public which has measurably better perplexity and lower English leak.

Measured baseline (Devin audit, CPU bf16, 50 short Indonesian sentences)

Metric	Value
Perplexity	9.9 (vs 8.4 for v5-public)
English-stopword ratio in ID-prompted output	3.6% (vs 0.9% for v5-public)
Indonesian-stopword ratio in ID-prompted output	26.8%
Parameters	1777.1 M
Architecture	Qwen2ForCausalLM

Status

Kept for historical reference / reproducibility. For new downstream work, use AksaraLLM-Qwen-1.5B-v5-public instead.

License

Apache 2.0

Downloads last month: 27

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for AksaraLLM/aksarallm-1.5b-v2-checkpoint

Base model

Qwen/Qwen2-1.5B

Finetuned

(84)

this model