Instructions to use krytonguard/java-starcoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use krytonguard/java-starcoder with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("bigcode/starcoderbase-1b")
model = PeftModel.from_pretrained(base_model, "krytonguard/java-starcoder")

Transformers

How to use krytonguard/java-starcoder with Transformers:

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

pipe = pipeline("text-generation", model="krytonguard/java-starcoder")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("krytonguard/java-starcoder", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use krytonguard/java-starcoder with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/krytonguard/java-starcoder

SGLang

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

Docker Model Runner
How to use krytonguard/java-starcoder with Docker Model Runner:
```
docker model run hf.co/krytonguard/java-starcoder
```

krytonguard commited on Nov 23, 2025

Commit

81ac13e

verified ·

1 Parent(s): 7cfce68

Training in progress, step 2100

Browse files

Files changed (1) hide show

adapter_model.safetensors +1 -1

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d0c6d90a134a9d51d89e4c10d97c2e8cfcec09ddfbf98816e92fbfeb952e6a9
 size 5578432

 version https://git-lfs.github.com/spec/v1
+oid sha256:530a2d443d0bbf8b0e087f75903079ec27d46b7b659389f117fcf64c1b31a2bb
 size 5578432