Instructions to use thealper2/codet5-base-code-repair with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thealper2/codet5-base-code-repair with Transformers:

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

pipe = pipeline("text-generation", model="thealper2/codet5-base-code-repair")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("thealper2/codet5-base-code-repair")
model = AutoModelForSeq2SeqLM.from_pretrained("thealper2/codet5-base-code-repair", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use thealper2/codet5-base-code-repair with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thealper2/codet5-base-code-repair"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thealper2/codet5-base-code-repair",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/thealper2/codet5-base-code-repair

SGLang

How to use thealper2/codet5-base-code-repair 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 "thealper2/codet5-base-code-repair" \
    --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": "thealper2/codet5-base-code-repair",
		"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 "thealper2/codet5-base-code-repair" \
        --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": "thealper2/codet5-base-code-repair",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use thealper2/codet5-base-code-repair with Docker Model Runner:
```
docker model run hf.co/thealper2/codet5-base-code-repair
```

codet5-base-code-repair / run_config.json

thealper2

Upload folder using huggingface_hub

9215e6b verified 19 days ago

Raw History Blame Contribute Delete

1.44 kB

	{
	"model_name": "Salesforce/codet5-base",
	"dataset_name": "google/code_x_glue_cc_code_refinement",
	"dataset_config": "small",
	"source_column": null,
	"target_column": null,
	"language": "java",
	"train_split": "train",
	"eval_split": "validation",
	"test_split": "test",
	"max_source_length": 256,
	"max_target_length": 256,
	"pad_to_multiple_of": 8,
	"learning_rate": 5e-05,
	"per_device_train_batch_size": 16,
	"per_device_eval_batch_size": 64,
	"gradient_accumulation_steps": 2,
	"num_train_epochs": 10.0,
	"weight_decay": 0.01,
	"warmup_ratio": 0.05,
	"lr_scheduler_type": "linear",
	"max_grad_norm": 1.0,
	"label_smoothing_factor": 0.0,
	"gradient_checkpointing": false,
	"eval_strategy": "epoch",
	"save_strategy": "epoch",
	"logging_steps": 100,
	"save_total_limit": 2,
	"load_best_model_at_end": true,
	"metric_for_best_model": "exact_match",
	"greater_is_better": true,
	"early_stopping_patience": 3,
	"eval_subset_size": 1000,
	"max_eval_examples": 0,
	"num_beams": 4,
	"max_new_tokens": 256,
	"generation_early_stopping": true,
	"length_penalty": 1.0,
	"no_repeat_ngram_size": 0,
	"seed": 42,
	"output_dir": "outputs/codet5-base-code-repair",
	"precision": "auto",
	"dataloader_num_workers": 4,
	"report_to": "none",
	"resume_from_checkpoint": null,
	"compute_codebleu": true,
	"smoke_test": false,
	"smoke_train_size": 256,
	"smoke_eval_size": 32,
	"smoke_epochs": 1.0
	}