Instructions to use Rakhman16/program-synthesis-java-codet5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Rakhman16/program-synthesis-java-codet5 with Transformers:

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

pipe = pipeline("text-generation", model="Rakhman16/program-synthesis-java-codet5")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("Rakhman16/program-synthesis-java-codet5")
model = AutoModelForSeq2SeqLM.from_pretrained("Rakhman16/program-synthesis-java-codet5")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Rakhman16/program-synthesis-java-codet5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Rakhman16/program-synthesis-java-codet5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rakhman16/program-synthesis-java-codet5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Rakhman16/program-synthesis-java-codet5

SGLang

How to use Rakhman16/program-synthesis-java-codet5 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 "Rakhman16/program-synthesis-java-codet5" \
    --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": "Rakhman16/program-synthesis-java-codet5",
		"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 "Rakhman16/program-synthesis-java-codet5" \
        --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": "Rakhman16/program-synthesis-java-codet5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Rakhman16/program-synthesis-java-codet5 with Docker Model Runner:
```
docker model run hf.co/Rakhman16/program-synthesis-java-codet5
```

Rakhman16 commited on Dec 9, 2024

Commit

37b03c3

verified ·

1 Parent(s): 76489d3

Training in progress, epoch 1, checkpoint

Browse files

Files changed (2) hide show

last-checkpoint/trainer_state.json +3 -3
last-checkpoint/training_args.bin +1 -1

last-checkpoint/trainer_state.json CHANGED Viewed

@@ -25,9 +25,9 @@
     {
       "epoch": 1.0,
       "eval_loss": 0.3516891300678253,
-      "eval_runtime": 35.1495,
-      "eval_samples_per_second": 14.054,
-      "eval_steps_per_second": 1.764,
       "step": 1203
     }
   ],

     {
       "epoch": 1.0,
       "eval_loss": 0.3516891300678253,
+      "eval_runtime": 35.0969,
+      "eval_samples_per_second": 14.075,
+      "eval_steps_per_second": 1.767,
       "step": 1203
     }
   ],

last-checkpoint/training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ba79581b87a766ba3cfbad453303b24f11dd2ee5f6d48404b72e1870492f394
 size 5496

 version https://git-lfs.github.com/spec/v1
+oid sha256:95c83942aa32bcf2e00ad7dbd24478e22e23c6cfe5e0b0c7d6ecdeaf3ca0b996
 size 5496